Jens Lehmann

Chengjin Xu, Fenglong Su, Jens Lehmann

Entity alignment aims to identify equivalent entity pairs between different knowledge graphs (KGs). Recently, the availability of temporal KGs (TKGs) that contain time information created the need for reasoning over time in such TKGs. Existing embedding-based entity alignment approaches disregard time information that commonly exists in many large-scale KGs, leaving much room for improvement. In this paper, we focus on the task of aligning entity pairs between TKGs and propose a novel Time-aware Entity Alignment approach based on Graph Neural Networks (TEA-GNN). We embed entities, relations and timestamps of different KGs into a vector space and use GNNs to learn entity representations. To incorporate both relation and time information into the GNN structure of our model, we use a time-aware attention mechanism which assigns different weights to different nodes with orthogonal transformation matrices computed from embeddings of the relevant relations and timestamps in a neighborhood. Experimental results on multiple real-world TKG datasets show that our method significantly outperforms the state-of-the-art methods due to the inclusion of time information.

Md Rashad Al Hasan Rony, Ricardo Usbeck, Jens Lehmann

Task-oriented dialogue generation is challenging since the underlying knowledge is often dynamic and effectively incorporating knowledge into the learning process is hard. It is particularly challenging to generate both human-like and informative responses in this setting. Recent research primarily focused on various knowledge distillation methods where the underlying relationship between the facts in a knowledge base is not effectively captured. In this paper, we go one step further and demonstrate how the structural information of a knowledge graph can improve the system's inference capabilities. Specifically, we propose DialoKG, a novel task-oriented dialogue system that effectively incorporates knowledge into a language model. Our proposed system views relational knowledge as a knowledge graph and introduces (1) a structure-aware knowledge embedding technique, and (2) a knowledge graph-weighted attention masking strategy to facilitate the system selecting relevant information during the dialogue generation. An empirical evaluation demonstrates the effectiveness of DialoKG over state-of-the-art methods on several standard benchmark datasets.

Karishma Mohiuddin, Mirza Ariful Alam, Mirza Mohtashim Alam et al.

Skilled employees are the most important pillars of an organization. Despite this, most organizations face high attrition and turnover rates. While several machine learning models have been developed to analyze attrition and its causal factors, the interpretations of those models remain opaque. In this paper, we propose the HR-DSS approach, which stands for Human Resource (HR) Decision Support System, and uses explainable AI for employee attrition problems. The system is designed to assist HR departments in interpreting the predictions provided by machine learning models. In our experiments, we employ eight machine learning models to provide predictions. We further process the results achieved by the best-performing model by the SHAP explainability process and use the SHAP values to generate natural language explanations which can be valuable for HR. Furthermore, using "What-if-analysis", we aim to observe plausible causes for attrition of an individual employee. The results show that by adjusting the specific dominant features of each individual, employee attrition can turn into employee retention through informative business decisions.

Md Rashad Al Hasan Rony, Liubov Kovriguina, Debanjan Chaudhuri et al.

Evaluating Natural Language Generation (NLG) systems is a challenging task. Firstly, the metric should ensure that the generated hypothesis reflects the reference's semantics. Secondly, it should consider the grammatical quality of the generated sentence. Thirdly, it should be robust enough to handle various surface forms of the generated sentence. Thus, an effective evaluation metric has to be multifaceted. In this paper, we propose an automatic evaluation metric incorporating several core aspects of natural language understanding (language competence, syntactic and semantic variation). Our proposed metric, RoMe, is trained on language features such as semantic similarity combined with tree edit distance and grammatical acceptability, using a self-supervised neural network to assess the overall quality of the generated sentence. Moreover, we perform an extensive robustness analysis of the state-of-the-art methods and RoMe. Empirical results suggest that RoMe has a stronger correlation to human judgment over state-of-the-art metrics in evaluating system-generated sentences across several NLG tasks.

Endri Kacupaj, Kuldeep Singh, Maria Maleshkova et al.

This paper addresses the task of conversational question answering (ConvQA) over knowledge graphs (KGs). The majority of existing ConvQA methods rely on full supervision signals with a strict assumption of the availability of gold logical forms of queries to extract answers from the KG. However, creating such a gold logical form is not viable for each potential question in a real-world scenario. Hence, in the case of missing gold logical forms, the existing information retrieval-based approaches use weak supervision via heuristics or reinforcement learning, formulating ConvQA as a KG path ranking problem. Despite missing gold logical forms, an abundance of conversational contexts, such as entire dialog history with fluent responses and domain information, can be incorporated to effectively reach the correct KG path. This work proposes a contrastive representation learning-based approach to rank KG paths effectively. Our approach solves two key challenges. Firstly, it allows weak supervision-based learning that omits the necessity of gold annotations. Second, it incorporates the conversational context (entire dialog history and domain information) to jointly learn its homogeneous representation with KG paths to improve contrastive representations for effective path ranking. We evaluate our approach on standard datasets for ConvQA, on which it significantly outperforms existing baselines on all domains and overall. Specifically, in some cases, the Mean Reciprocal Rank (MRR) and Hit@5 ranking metrics improve by absolute 10 and 18 points, respectively, compared to the state-of-the-art performance.

Mojtaba Nayyeri, Zihao Wang, Mst. Mahfuja Akter et al.

Knowledge Graphs, such as Wikidata, comprise structural and textual knowledge in order to represent knowledge. For each of the two modalities dedicated approaches for graph embedding and language models learn patterns that allow for predicting novel structural knowledge. Few approaches have integrated learning and inference with both modalities and these existing ones could only partially exploit the interaction of structural and textual knowledge. In our approach, we build on existing strong representations of single modalities and we use hypercomplex algebra to represent both, (i), single-modality embedding as well as, (ii), the interaction between different modalities and their complementary means of knowledge representation. More specifically, we suggest Dihedron and Quaternion representations of 4D hypercomplex numbers to integrate four modalities namely structural knowledge graph embedding, word-level representations (e.g.\ Word2vec, Fasttext), sentence-level representations (Sentence transformer), and document-level representations (sentence transformer, Doc2vec). Our unified vector representation scores the plausibility of labelled edges via Hamilton and Dihedron products, thus modeling pairwise interactions between different modalities. Extensive experimental evaluation on standard benchmark datasets shows the superiority of our two new models using abundant textual information besides sparse structural knowledge to enhance performance in link prediction tasks.

Md Rashad Al Hasan Rony, Mirza Mohtashim Alam, Semab Ali et al.

Knowledge Graph Embedding models have become an important area of machine learning.Those models provide a latent representation of entities and relations in a knowledge graph which can then be used in downstream machine learning tasks such as link prediction. The learning process of such models can be performed by contrasting positive and negative triples. While all triples of a KG are considered positive, negative triples are usually not readily available. Therefore, the choice of the sampling method to obtain the negative triples play a crucial role in the performance and effectiveness of Knowledge Graph Embedding models. Most of the current methods fetch negative samples from a random distribution of entities in the underlying Knowledge Graph which also often includes meaningless triples. Other known methods use adversarial techniques or generative neural networks which consequently reduce the efficiency of the process. In this paper, we propose an approach for generating informative negative samples considering available complementary knowledge about entities. Particularly, Pre-trained Language Models are used to form neighborhood clusters by utilizing the distances between entities to obtain representations of symbolic entities via their textual information. Our comprehensive evaluations demonstrate the effectiveness of the proposed approach on benchmark Knowledge Graphs with textual information for the link prediction task.

Klaudia-Doris Thellmann, Bernhard Stadler, Michael Färber et al.

Machine-translated benchmarks are widely used to assess the multilingual capabilities of large language models (LLMs), yet translation errors in these benchmarks remain underexplored, raising concerns about the reliability and comparability of multilingual evaluation. We address two practical gaps: (i) how well automatic MQM-style error spans from LLM judges and a span-aware QE baseline (xCOMET-XXL) match expert human span annotations on benchmark translations, and (ii) how strongly translation errors (as opposed to source-side issues in the English original) explain accuracy drops on translated benchmarks. We find that span agreement is non-trivial on naturally occurring benchmark translations, and that target-side translation errors are consistently associated with measurable, percentage-point drops in translated accuracy even after controlling for English correctness and source-side anomalies.

Klaudia-Doris Thellmann, Bernhard Stadler, Ricardo Usbeck et al.

While a considerable amount of semantic parsing approaches have employed RNN architectures for code generation tasks, there have been only few attempts to investigate the applicability of Transformers for this task. Including hierarchical information of the underlying programming language syntax has proven to be effective for code generation. Since the positional encoding of the Transformer can only represent positions in a flat sequence, we have extended the encoding scheme to allow the attention mechanism to also attend over hierarchical positions in the input. Furthermore, we have realized a decoder based on a restrictive grammar graph model to improve the generation accuracy and ensure the well-formedness of the generated code. While we did not surpass the state of the art, our findings suggest that employing a tree-based positional encoding in combination with a shared natural-language subword vocabulary improves generation performance over sequential positional encodings.

Mengying Wang, Nicolaas Jedema, Rahul Pandey et al.

Knowledge Graph Question Answering (KGQA) has advanced through structured query generation, yet most efforts target RDF/SPARQL, leaving Cypher and property graphs underexplored, despite increasing demand for unified KGQA in industry settings. We propose UniQGen, a novel constraint-based framework that employs LLM agents to dynamically extract and refine representative graph query clauses into executable, intent-aligned graph queries across query languages. The foundation of our method is a variant of Chase & Backchase, a family of algorithms for query optimization and reformulation. We extend Chase & Backchase with a dynamic reasoning process over query constraints that also interact with LLMs for query quality estimation. With a Cypher-supported Freebase graph deployed on Amazon Neptune, we extensively evaluate our approach on popular KGQA benchmarks (GraphQ, GrailQA, and WebQSP). We demonstrate that UniQGen outperforms state-of-the-art graph query generation techniques in both accuracy and efficiency, with F1 gains of 31.6% on GraphQ and 4.9% on GrailQA. Unlike prior methods, our framework does not require fine-tuning for schema matching, making it more extensible to schema-less graphs and semantics in query workloads, and is more suitable for enterprise-grade KGQA. We release Cypher outputs and a Neptune-ready Freebase snapshot to support reproducible, cross-language KGQA research.

Endri Kacupaj, Kuldeep Singh, Maria Maleshkova et al.

We introduce a new dataset for conversational question answering over Knowledge Graphs (KGs) with verbalized answers. Question answering over KGs is currently focused on answer generation for single-turn questions (KGQA) or multiple-tun conversational question answering (ConvQA). However, in a real-world scenario (e.g., voice assistants such as Siri, Alexa, and Google Assistant), users prefer verbalized answers. This paper contributes to the state-of-the-art by extending an existing ConvQA dataset with multiple paraphrased verbalized answers. We perform experiments with five sequence-to-sequence models on generating answer responses while maintaining grammatical correctness. We additionally perform an error analysis that details the rates of models' mispredictions in specified categories. Our proposed dataset extended with answer verbalization is publicly available with detailed documentation on its usage for wider utility.

Zheng Zhao, Emilio Monti, Jens Lehmann et al. · amazon-science

Large language models (LLMs) tend to inadequately integrate input context during text generation, relying excessively on encoded prior knowledge in model parameters, potentially resulting in generated text with factual inconsistencies or contextually unfaithful content. LLMs utilize two primary knowledge sources: 1) prior (parametric) knowledge from pretraining, and 2) contextual (non-parametric) knowledge from input prompts. The study addresses the open question of how LLMs effectively balance these knowledge sources during the generation process, specifically in the context of open-domain question answering. To address this issue, we introduce a novel approach integrating contrastive decoding with adversarial irrelevant passages as negative samples to enhance robust context grounding during generation. Notably, our method operates at inference time without requiring further training. We conduct comprehensive experiments to demonstrate its applicability and effectiveness, providing empirical evidence showcasing its superiority over existing methodologies. Our code is publicly available at: https://github.com/amazon-science/ContextualUnderstanding-ContrastiveDecoding.

Nacime Bouziani, Shubhi Tyagi, Joseph Fisher et al.

Extracting structured information from unstructured text is critical for many downstream NLP applications and is traditionally achieved by closed information extraction (cIE). However, existing approaches for cIE suffer from two limitations: (i) they are often pipelines which makes them prone to error propagation, and/or (ii) they are restricted to sentence level which prevents them from capturing long-range dependencies and results in expensive inference time. We address these limitations by proposing REXEL, a highly efficient and accurate model for the joint task of document level cIE (DocIE). REXEL performs mention detection, entity typing, entity disambiguation, coreference resolution and document-level relation classification in a single forward pass to yield facts fully linked to a reference knowledge graph. It is on average 11 times faster than competitive existing approaches in a similar setting and performs competitively both when optimised for any of the individual subtasks and a variety of combinations of different joint tasks, surpassing the baselines by an average of more than 6 F1 points. The combination of speed and accuracy makes REXEL an accurate cost-efficient system for extracting structured information at web-scale. We also release an extension of the DocRED dataset to enable benchmarking of future work on DocIE, which is available at https://github.com/amazon-science/e2e-docie.

Jens Lehmann, Syeda Khushbakht, Nikoo Salehfard et al.

The Abstraction and Reasoning Corpus (ARC-AGI) probes few-shot abstraction and rule induction on small visual grids, but progress is difficult to measure on static collections of hand-authored puzzles due to overfitting, dataset leakage, and memorisation. We introduce ARC-TGI (ARC Task Generators Inventory), an open-source framework for task-family generators: compact Python programs that sample diverse ARC-AGI tasks while preserving a latent rule. ARC-TGI is built around a solver-facing representation: each generated task is paired with natural-language input and transformation reasoning chains and partially evaluated Python code implementing sampling, transformation, and episode construction. Crucially, ARC-TGI supports task-level constraints so that training examples collectively expose the variations needed to infer the underlying rule, a requirement for human-solvable ARC tasks that independent per-example sampling often fails to guarantee. All generators undergo human refinement and local verification to keep both grids and reasoning traces natural and consistent under variation. We release 461 generators covering 180 ARC-Mini tasks, 215 ARC-AGI-1 tasks (200 train, 15 test), and 66 ARC-AGI-2 tasks (55 train, 11 test), enabling scalable dataset sampling and controlled benchmarking.

Riccardo Pozzi, Matteo Palmonari, Andrea Coletta et al.

Knowledge gaps and hallucinations are persistent challenges for Large Language Models (LLMs), which generate unreliable responses when lacking the necessary information to fulfill user instructions. Existing approaches, such as Retrieval-Augmented Generation (RAG) and tool use, aim to address these issues by incorporating external knowledge. Yet, they rely on additional models or services, resulting in complex pipelines, potential error propagation, and often requiring the model to process a large number of tokens. In this paper, we present a scalable method that enables LLMs to access external knowledge without depending on retrievers or auxiliary models. Our approach uses constrained generation with a pre-built prefix-tree index. Triples from a Knowledge Graph are verbalized in textual facts, tokenized, and indexed in a prefix tree for efficient access. During inference, to acquire external knowledge, the LLM generates facts with constrained generation which allows only sequences of tokens that form an existing fact. We evaluate our proposal on Question Answering and show that it scales to large knowledge bases (800 million facts), adapts to domain-specific data, and achieves effective results. These gains come with minimal generation-time overhead. ReFactX code is available at https://github.com/rpo19/ReFactX.

Mehdi Ali, Max Berrendorf, Mikhail Galkin et al.

For many years, link prediction on knowledge graphs (KGs) has been a purely transductive task, not allowing for reasoning on unseen entities. Recently, increasing efforts are put into exploring semi- and fully inductive scenarios, enabling inference over unseen and emerging entities. Still, all these approaches only consider triple-based \glspl{kg}, whereas their richer counterparts, hyper-relational KGs (e.g., Wikidata), have not yet been properly studied. In this work, we classify different inductive settings and study the benefits of employing hyper-relational KGs on a wide range of semi- and fully inductive link prediction tasks powered by recent advancements in graph neural networks. Our experiments on a novel set of benchmarks show that qualifiers over typed edges can lead to performance improvements of 6% of absolute gains (for the Hits@10 metric) compared to triple-only baselines. Our code is available at \url{https://github.com/mali-git/hyper_relational_ilp}.

Mehdi Ali, Max Berrendorf, Charles Tapley Hoyt et al.

The heterogeneity in recently published knowledge graph embedding models' implementations, training, and evaluation has made fair and thorough comparisons difficult. In order to assess the reproducibility of previously published results, we re-implemented and evaluated 21 interaction models in the PyKEEN software package. Here, we outline which results could be reproduced with their reported hyper-parameters, which could only be reproduced with alternate hyper-parameters, and which could not be reproduced at all as well as provide insight as to why this might be the case. We then performed a large-scale benchmarking on four datasets with several thousands of experiments and 24,804 GPU hours of computation time. We present insights gained as to best practices, best configurations for each model, and where improvements could be made over previously published best configurations. Our results highlight that the combination of model architecture, training approach, loss function, and the explicit modeling of inverse relations is crucial for a model's performances, and not only determined by the model architecture. We provide evidence that several architectures can obtain results competitive to the state-of-the-art when configured carefully. We have made all code, experimental configurations, results, and analyses that lead to our interpretations available at https://github.com/pykeen/pykeen and https://github.com/pykeen/benchmarking

Mohammad Rezaei, Jens Lehmann, Sahar Vahdati

Mathematical reasoning in large language models has improved substantially with reinforcement learning using verifiable rewards, where final answers can be checked automatically and converted into reliable training signals. Most such pipelines optimize outcome correctness only, which yields sparse feedback for long, multi-step solutions and offers limited guidance on intermediate reasoning errors. Recent work therefore introduces process reward models (PRMs) to score intermediate steps and provide denser supervision. In practice, PRM scores are often imperfectly aligned with final correctness and can reward locally fluent reasoning that still ends in an incorrect answer. When optimized as absolute rewards, such signals can amplify fluent failure modes and induce reward hacking. We propose PROGRS, a framework that leverages PRMs while keeping outcome correctness dominant. PROGRS treats process rewards as relative preferences within outcome groups rather than absolute targets. We introduce outcome-conditioned centering, which shifts PRM scores of incorrect trajectories to have zero mean within each prompt group. It removes systematic bias while preserving informative rankings. PROGRS combines a frozen quantile-regression PRM with a multi-scale coherence evaluator. We integrate the resulting centered process bonus into Group Relative Policy Optimization (GRPO) without auxiliary objectives or additional trainable components. Across MATH-500, AMC, AIME, MinervaMath, and OlympiadBench, PROGRS consistently improves Pass@1 over outcome-only baselines and achieves stronger performance with fewer rollouts. These results show that outcome-conditioned centering enables safe and effective use of process rewards for mathematical reasoning.

Sahar Vahdati, Andrei Aioanei, Haridhra Suresh et al.

The Abstraction and Reasoning Corpus (ARC-AGI) has become a key benchmark for fluid intelligence in AI. This survey presents the first cross-generation analysis of 82 approaches across three benchmark versions and the ARC Prize 2024-2025 competitions. Our central finding is that performance degradation across versions is consistent across all paradigms: program synthesis, neuro-symbolic, and neural approaches all exhibit 2-3x drops from ARC-AGI-1 to ARC-AGI-2, indicating fundamental limitations in compositional generalization. While systems now reach 93.0% on ARC-AGI-1 (Opus 4.6), performance falls to 68.8% on ARC-AGI-2 and 13% on ARC-AGI-3, as humans maintain near-perfect accuracy across all versions. Cost fell 390x in one year (o3's $4,500/task to GPT-5.2's $12/task), although this largely reflects reduced test-time parallelism. Trillion-scale models vary widely in score and cost, while Kaggle-constrained entries (660M-8B) achieve competitive results, aligning with Chollet's thesis that intelligence is skill-acquisition efficiency. Test-time adaptation and refinement loops emerge as critical success factors, while compositional reasoning and interactive learning remain unsolved. ARC Prize 2025 winners needed hundreds of thousands of synthetic examples to reach 24% on ARC-AGI-2, confirming that reasoning remains knowledge-bound. This first release of the ARC-AGI Living Survey captures the field as of February 2026, with updates at https://nimi-ai.com/arc-survey/

Kossi Amouzouvi, Robert Wardenga, Jens Lehmann et al.

Foundation models excel at language, where sentences become tokens, and vision, where images become pixels, because both reduce to discrete symbols on a shared, fixed grid. Knowledge Graphs share the discreteness, but not the geometry. Their entities and relations are discrete symbols, yet their arrangement is relational and lacks a common, fixed grid. Knowledge Graphs (KGs) share the discreteness, but not the geometry. They form irregular, non-Euclidean topologies whose local neighborhoods differ from graph to graph. Therefore, Knowledge Graph Foundation Models (KGFMs) rely on identifying structural invariances to produce transferable representations. Without a universal token set, KGFMs are limited in their ability to transfer representations across unseen KGs. We close this gap by treating graphlets, small connected graphs, as structural tokens that recur in heterogeneous KGs. In this paper, We introduce a model-agnostic framework based on a vocabulary of graphlets that mines a KG between relations via pattern matching. In particular, we considered closed and open 2- and 3-path, and star graphlets, to obtain robust invariances. The framework is evaluated on 51 KGs from a wide range of domains, for zero-shot inductive and transductive link prediction. Experiments show that adding simple graphlets to the vocabulary yields models that outperform prior KGFMs.

Alexander Arno Weber, Klaudia Thellmann, Jan Ebert et al.

The adaption of multilingual pre-trained LLMs into eloquent and helpful assistants is essential to facilitate their use across different language regions. In that spirit, we are the first to conduct an extensive study of the performance of multilingual models instruction-tuned on different language compositions on parallel instruction-tuning benchmarks across a selection of the most spoken Indo-European languages. We systematically examine the effects of language and instruction dataset size on a mid-sized and a large, multilingual LLMs by instruction-tuning them on parallel instruction-tuning datasets. Our results demonstrate that instruction-tuning on parallel instead of monolingual corpora benefits cross-lingual instruction following capabilities by up to 9.9%. Furthermore, we show that the Superficial Alignment Hypothesis does not hold in general, as the investigated multilingual 7B parameter model presents a counter-example requiring large-scale instruction-tuning datasets. Finally, we conduct a human annotation study to understand the alignment between human-based and GPT-4-based evaluation within multilingual chat scenarios.

Md Rashad Al Hasan Rony, Sudipto Kumar Shaha, Rakib Al Hasan et al.

Bengali is the seventh most spoken language on earth, yet considered a low-resource language in the field of natural language processing (NLP). Question answering over unstructured text is a challenging NLP task as it requires understanding both question and passage. Very few researchers attempted to perform question answering over Bengali (natively pronounced as Bangla) text. Typically, existing approaches construct the dataset by directly translating them from English to Bengali, which produces noisy and improper sentence structures. Furthermore, they lack topics and terminologies related to the Bengali language and people. This paper introduces BanglaQuAD, a Bengali question answering dataset, containing 30,808 question-answer pairs constructed from Bengali Wikipedia articles by native speakers. Additionally, we propose an annotation tool that facilitates question-answering dataset construction on a local machine. A qualitative analysis demonstrates the quality of our proposed dataset.

Nur A Zarin Nishat, Andrea Coletta, Luigi Bellomarini et al.

Large language models like GPT-4, Gemini, and Claude have transformed natural language processing (NLP) tasks such as question answering, dialogue generation, summarization, and so forth; yet their susceptibility to hallucination stands as one of the major challenges. Among numerous approaches to overcome this challenge, integration of Knowledge Graphs (KGs) into language models has emerged as a promising solution as it provides structured, reliable, domain-specific, and up-to-date external information to the language models. In this paper, we introduce ALIGNed-LLM, a simple yet effective approach to improve language models' factuality via a lean strategy to infuse KGs into the latent space of language models inspired by LLaVA where visual and textual information is infused. We use embeddings from a pre-trained Knowledge Graph Embedding (KGE) model, such as TransE, and a trainable projection layer to align entity and text embeddings. This alignment enables the language model to distinguish between similar entities improving factual grounding and reducing hallucination. We tested our approach on three popular questions-answering benchmark datasets alongside language models of varying sizes, showing significant improvement. Furthermore, we applied our approach to a real-world financial use case from a large central bank in Europe, which demands high accuracy and precision, demonstrating a substantial improvement of the LLM answers.

Muhammad Hamza Yousuf, Jason Li, Sahar Vahdati et al.

Invasive mechanical ventilation (MV) is a life-sustaining therapy for critically ill patients in the intensive care unit (ICU). However, optimizing its settings remains a complex and error-prone process due to patient-specific variability. While Offline Reinforcement Learning (RL) shows promise for MV control, current stateof-the-art (SOTA) methods struggle with the hybrid (continuous and discrete) nature of MV actions. Discretizing the action space limits available actions due to exponential growth in combinations and introduces distribution shifts that can compromise safety. In this paper, we propose optimizations that build upon prior work in action space reduction to address the challenges of discrete action spaces. We also adapt SOTA offline RL algorithms (IQL and EDAC) to operate directly on hybrid action spaces, thereby avoiding the pitfalls of discretization. Additionally, we introduce a clinically grounded reward function based on ventilator-free days and physiological targets, which provides a more meaningful optimization objective compared to traditional sparse mortality-based rewards. Our findings demonstrate that AI-assisted MV optimization may enhance patient safety and enable individualized lung support, representing a significant advancement toward intelligent, data-driven critical care solutions.

Kossi Amouzouvi, Bowen Song, Andrea Coletta et al.

Knowledge graph representation learning approaches provide a mapping between symbolic knowledge in the form of triples in a knowledge graph (KG) and their feature vectors. Knowledge graph embedding (KGE) models often represent relations in a KG as geometric transformations. Most state-of-the-art (SOTA) KGE models are derived from elementary geometric transformations (EGTs), such as translation, scaling, rotation, and reflection, or their combinations. These geometric transformations enable the models to effectively preserve specific structural and relational patterns of the KG. However, the current use of EGTs by KGEs remains insufficient without considering relation-specific transformations. Although recent models attempted to address this problem by ensembling SOTA baseline models in different ways, only a single or composite version of geometric transformations are used by such baselines to represent all the relations. In this paper, we propose a framework that evaluates how well each relation fits with different geometric transformations. Based on this ranking, the model can: (1) assign the best-matching transformation to each relation, or (2) use majority voting to choose one transformation type to apply across all relations. That is, the model learns a single relation-specific EGT in low dimensional vector space through an attention mechanism. Furthermore, we use the correlation between relations and EGTs, which are learned in a low dimension, for relation embeddings in a high dimensional vector space. The effectiveness of our models is demonstrated through comprehensive evaluations on three benchmark KGs as well as a real-world financial KG, witnessing a performance comparable to leading models

Dongkyu Lee, Chandana Satya Prakash, Jack FitzGerald et al.

Leveraging external knowledge is crucial for achieving high performance in knowledge-intensive tasks, such as question answering. The retrieve-and-read approach is widely adopted for integrating external knowledge into a language model. However, this approach suffers from increased computational cost and latency due to the long context length, which grows proportionally with the number of retrieved knowledge. Furthermore, existing retrieval-augmented models typically retrieve information from a single type of knowledge source, limiting their scalability to diverse knowledge sources with varying structures. In this work, we introduce an efficient memory-augmented transformer called MATTER, designed to retrieve relevant knowledge from multiple heterogeneous knowledge sources. Specifically, our model retrieves and reads from both unstructured sources (paragraphs) and semi-structured sources (QA pairs) in the form of fixed-length neural memories. We demonstrate that our model outperforms existing efficient retrieval-augmented models on popular QA benchmarks in terms of both accuracy and speed. Furthermore, MATTER achieves competitive results compared to conventional read-and-retrieve models while having 100x throughput during inference.

Chengjin Xu, Mojtaba Nayyeri, Yung-Yu Chen et al.

Recent years, Knowledge Graph Embeddings (KGEs) have shown promising performance on link prediction tasks by mapping the entities and relations from a Knowledge Graph (KG) into a geometric space and thus have gained increasing attentions. In addition, many recent Knowledge Graphs involve evolving data, e.g., the fact (\textit{Obama}, \textit{PresidentOf}, \textit{USA}) is valid only from 2009 to 2017. This introduces important challenges for knowledge representation learning since such temporal KGs change over time. In this work, we strive to move beyond the complex or hypercomplex space for KGE and propose a novel geometric algebra based embedding approach, GeomE, which uses multivector representations and the geometric product to model entities and relations. GeomE subsumes several state-of-the-art KGE models and is able to model diverse relations patterns. On top of this, we extend GeomE to TGeomE for temporal KGE, which performs 4th-order tensor factorization of a temporal KG and devises a new linear temporal regularization for time representation learning. Moreover, we study the effect of time granularity on the performance of TGeomE models. Experimental results show that our proposed models achieve the state-of-the-art performances on link prediction over four commonly-used static KG datasets and four well-established temporal KG datasets across various metrics.

Nandana Mihindukulasooriya, Mohnish Dubey, Alfio Gliozzo et al.

Each year the International Semantic Web Conference organizes a set of Semantic Web Challenges to establish competitions that will advance state-of-the-art solutions in some problem domains. The Semantic Answer Type and Relation Prediction Task (SMART) task is one of the ISWC 2021 Semantic Web challenges. This is the second year of the challenge after a successful SMART 2020 at ISWC 2020. This year's version focuses on two sub-tasks that are very important to Knowledge Base Question Answering (KBQA): Answer Type Prediction and Relation Prediction. Question type and answer type prediction can play a key role in knowledge base question answering systems providing insights about the expected answer that are helpful to generate correct queries or rank the answer candidates. More concretely, given a question in natural language, the first task is, to predict the answer type using a target ontology (e.g., DBpedia or Wikidata. Similarly, the second task is to identify relations in the natural language query and link them to the relations in a target ontology. This paper discusses the task descriptions, benchmark datasets, and evaluation metrics. For more information, please visit https://smart-task.github.io/2021/.

Cedric Möller, Jens Lehmann, Ricardo Usbeck

Wikidata is a frequently updated, community-driven, and multilingual knowledge graph. Hence, Wikidata is an attractive basis for Entity Linking, which is evident by the recent increase in published papers. This survey focuses on four subjects: (1) Which Wikidata Entity Linking datasets exist, how widely used are they and how are they constructed? (2) Do the characteristics of Wikidata matter for the design of Entity Linking datasets and if so, how? (3) How do current Entity Linking approaches exploit the specific characteristics of Wikidata? (4) Which Wikidata characteristics are unexploited by existing Entity Linking approaches? This survey reveals that current Wikidata-specific Entity Linking datasets do not differ in their annotation scheme from schemes for other knowledge graphs like DBpedia. Thus, the potential for multilingual and time-dependent datasets, naturally suited for Wikidata, is not lifted. Furthermore, we show that most Entity Linking approaches use Wikidata in the same way as any other knowledge graph missing the chance to leverage Wikidata-specific characteristics to increase quality. Almost all approaches employ specific properties like labels and sometimes descriptions but ignore characteristics such as the hyper-relational structure. Hence, there is still room for improvement, for example, by including hyper-relational graph embeddings or type information. Many approaches also include information from Wikipedia, which is easily combinable with Wikidata and provides valuable textual information, which Wikidata lacks.

Mojtaba Nayyeri, Gokce Muge Cil, Sahar Vahdati et al.

The incompleteness of Knowledge Graphs (KGs) is a crucial issue affecting the quality of AI-based services. In the scholarly domain, KGs describing research publications typically lack important information, hindering our ability to analyse and predict research dynamics. In recent years, link prediction approaches based on Knowledge Graph Embedding models became the first aid for this issue. In this work, we present Trans4E, a novel embedding model that is particularly fit for KGs which include N to M relations with N$\gg$M. This is typical for KGs that categorize a large number of entities (e.g., research articles, patents, persons) according to a relatively small set of categories. Trans4E was applied on two large-scale knowledge graphs, the Academia/Industry DynAmics (AIDA) and Microsoft Academic Graph (MAG), for completing the information about Fields of Study (e.g., 'neural networks', 'machine learning', 'artificial intelligence'), and affiliation types (e.g., 'education', 'company', 'government'), improving the scope and accuracy of the resulting data. We evaluated our approach against alternative solutions on AIDA, MAG, and four other benchmarks (FB15k, FB15k-237, WN18, and WN18RR). Trans4E outperforms the other models when using low embedding dimensions and obtains competitive results in high dimensions.

Endri Kacupaj, Shyamnath Premnadh, Kuldeep Singh et al.

In recent years, there have been significant developments in Question Answering over Knowledge Graphs (KGQA). Despite all the notable advancements, current KGQA systems only focus on answer generation techniques and not on answer verbalization. However, in real-world scenarios (e.g., voice assistants such as Alexa, Siri, etc.), users prefer verbalized answers instead of a generated response. This paper addresses the task of answer verbalization for (complex) question answering over knowledge graphs. In this context, we propose a multi-task-based answer verbalization framework: VOGUE (Verbalization thrOuGh mUlti-task lEarning). The VOGUE framework attempts to generate a verbalized answer using a hybrid approach through a multi-task learning paradigm. Our framework can generate results based on using questions and queries as inputs concurrently. VOGUE comprises four modules that are trained simultaneously through multi-task learning. We evaluate our framework on existing datasets for answer verbalization, and it outperforms all current baselines on both BLEU and METEOR scores.

Debanjali Biswas, Mohnish Dubey, Md Rashad Al Hasan Rony et al.

In the last years, there have been significant developments in the area of Question Answering over Knowledge Graphs (KGQA). Despite all the notable advancements, current KGQA datasets only provide the answers as the direct output result of the formal query, rather than full sentences incorporating question context. For achieving coherent answers sentence with the question's vocabulary, template-based verbalization so are usually employed for a better representation of answers, which in turn require extensive expert intervention. Thus, making way for machine learning approaches; however, there is a scarcity of datasets that empower machine learning models in this area. Hence, we provide the VANiLLa dataset which aims at reducing this gap by offering answers in natural language sentences. The answer sentences in this dataset are syntactically and semantically closer to the question than to the triple fact. Our dataset consists of over 100k simple questions adapted from the CSQA and SimpleQuestionsWikidata datasets and generated using a semi-automatic framework. We also present results of training our dataset on multiple baseline models adapted from current state-of-the-art Natural Language Generation (NLG) architectures. We believe that this dataset will allow researchers to focus on finding suitable methodologies and architectures for answer verbalization.

Golsa Tahmasebzadeh, Endri Kacupaj, Eric Müller-Budack et al.

In the context of social media, geolocation inference on news or events has become a very important task. In this paper, we present the GeoWINE (Geolocation-based Wiki-Image-News-Event retrieval) demonstrator, an effective modular system for multimodal retrieval which expects only a single image as input. The GeoWINE system consists of five modules in order to retrieve related information from various sources. The first module is a state-of-the-art model for geolocation estimation of images. The second module performs a geospatial-based query for entity retrieval using the Wikidata knowledge graph. The third module exploits four different image embedding representations, which are used to retrieve most similar entities compared to the input image. The embeddings are derived from the tasks of geolocation estimation, place recognition, ImageNet-based image classification, and their combination. The last two modules perform news and event retrieval from EventRegistry and the Open Event Knowledge Graph (OEKG). GeoWINE provides an intuitive interface for end-users and is insightful for experts for reconfiguration to individual setups. The GeoWINE achieves promising results in entity label prediction for images on Google Landmarks dataset. The demonstrator is publicly available at http://cleopatra.ijs.si/geowine/.

Chengjin Xu, Mojtaba Nayyeri, Sahar Vahdati et al.

Among the top approaches of recent years, link prediction using knowledge graph embedding (KGE) models has gained significant attention for knowledge graph completion. Various embedding models have been proposed so far, among which, some recent KGE models obtain state-of-the-art performance on link prediction tasks by using embeddings with a high dimension (e.g. 1000) which accelerate the costs of training and evaluation considering the large scale of KGs. In this paper, we propose a simple but effective performance boosting strategy for KGE models by using multiple low dimensions in different repetition rounds of the same model. For example, instead of training a model one time with a large embedding size of 1200, we repeat the training of the model 6 times in parallel with an embedding size of 200 and then combine the 6 separate models for testing while the overall numbers of adjustable parameters are same (6*200=1200) and the total memory footprint remains the same. We show that our approach enables different models to better cope with their expressiveness issues on modeling various graph patterns such as symmetric, 1-n, n-1 and n-n. In order to justify our findings, we conduct experiments on various KGE models. Experimental results on standard benchmark datasets, namely FB15K, FB15K-237 and WN18RR, show that multiple low-dimensional models of the same kind outperform the corresponding single high-dimensional models on link prediction in a certain range and have advantages in training efficiency by using parallel training while the overall numbers of adjustable parameters are same.

Endri Kacupaj, Joan Plepi, Kuldeep Singh et al.

This paper addresses the task of (complex) conversational question answering over a knowledge graph. For this task, we propose LASAGNE (muLti-task semAntic parSing with trAnsformer and Graph atteNtion nEtworks). It is the first approach, which employs a transformer architecture extended with Graph Attention Networks for multi-task neural semantic parsing. LASAGNE uses a transformer model for generating the base logical forms, while the Graph Attention model is used to exploit correlations between (entity) types and predicates to produce node representations. LASAGNE also includes a novel entity recognition module which detects, links, and ranks all relevant entities in the question context. We evaluate LASAGNE on a standard dataset for complex sequential question answering, on which it outperforms existing baseline averages on all question types. Specifically, we show that LASAGNE improves the F1-score on eight out of ten question types; in some cases, the increase in F1-score is more than 20% compared to the state of the art.

Debanjan Chaudhuri, Md Rashad Al Hasan Rony, Jens Lehmann

Generating knowledge grounded responses in both goal and non-goal oriented dialogue systems is an important research challenge. Knowledge Graphs (KG) can be viewed as an abstraction of the real world, which can potentially facilitate a dialogue system to produce knowledge grounded responses. However, integrating KGs into the dialogue generation process in an end-to-end manner is a non-trivial task. This paper proposes a novel architecture for integrating KGs into the response generation process by training a BERT model that learns to answer using the elements of the KG (entities and relations) in a multi-task, end-to-end setting. The k-hop subgraph of the KG is incorporated into the model during training and inference using Graph Laplacian. Empirical evaluation suggests that the model achieves better knowledge groundedness (measured via Entity F1 score) compared to other state-of-the-art models for both goal and non-goal oriented dialogues.

Endri Kacupaj, Barshana Banerjee, Kuldeep Singh et al.

This paper presents ParaQA, a question answering (QA) dataset with multiple paraphrased responses for single-turn conversation over knowledge graphs (KG). The dataset was created using a semi-automated framework for generating diverse paraphrasing of the answers using techniques such as back-translation. The existing datasets for conversational question answering over KGs (single-turn/multi-turn) focus on question paraphrasing and provide only up to one answer verbalization. However, ParaQA contains 5000 question-answer pairs with a minimum of two and a maximum of eight unique paraphrased responses for each question. We complement the dataset with baseline models and illustrate the advantage of having multiple paraphrased answers through commonly used metrics such as BLEU and METEOR. The ParaQA dataset is publicly available on a persistent URI for broader usage and adaptation in the research community.

Joan Plepi, Endri Kacupaj, Kuldeep Singh et al.

Neural semantic parsing approaches have been widely used for Question Answering (QA) systems over knowledge graphs. Such methods provide the flexibility to handle QA datasets with complex queries and a large number of entities. In this work, we propose a novel framework named CARTON, which performs multi-task semantic parsing for handling the problem of conversational question answering over a large-scale knowledge graph. Our framework consists of a stack of pointer networks as an extension of a context transformer model for parsing the input question and the dialog history. The framework generates a sequence of actions that can be executed on the knowledge graph. We evaluate CARTON on a standard dataset for complex sequential question answering on which CARTON outperforms all baselines. Specifically, we observe performance improvements in F1-score on eight out of ten question types compared to the previous state of the art. For logical reasoning questions, an improvement of 11 absolute points is reached.

Manoj Prabhakar Kannan Ravi, Kuldeep Singh, Isaiah Onando Mulang' et al.

In this paper, we propose CHOLAN, a modular approach to target end-to-end entity linking (EL) over knowledge bases. CHOLAN consists of a pipeline of two transformer-based models integrated sequentially to accomplish the EL task. The first transformer model identifies surface forms (entity mentions) in a given text. For each mention, a second transformer model is employed to classify the target entity among a predefined candidates list. The latter transformer is fed by an enriched context captured from the sentence (i.e. local context), and entity description gained from Wikipedia. Such external contexts have not been used in the state of the art EL approaches. Our empirical study was conducted on two well-known knowledge bases (i.e., Wikidata and Wikipedia). The empirical results suggest that CHOLAN outperforms state-of-the-art approaches on standard datasets such as CoNLL-AIDA, MSNBC, AQUAINT, ACE2004, and T-REx.

Nandana Mihindukulasooriya, Mohnish Dubey, Alfio Gliozzo et al.

Each year the International Semantic Web Conference accepts a set of Semantic Web Challenges to establish competitions that will advance the state of the art solutions in any given problem domain. The SeMantic AnsweR Type prediction task (SMART) was part of ISWC 2020 challenges. Question type and answer type prediction can play a key role in knowledge base question answering systems providing insights that are helpful to generate correct queries or rank the answer candidates. More concretely, given a question in natural language, the task of SMART challenge is, to predict the answer type using a target ontology (e.g., DBpedia or Wikidata).

Mojtaba Nayyeri, Chengjin Xu, Jens Lehmann et al.

Knowledge Graph Embeddings (KGEs) have shown promising performance on link prediction tasks by mapping the entities and relations from a knowledge graph into a geometric space (usually a vector space). Ultimately, the plausibility of the predicted links is measured by using a scoring function over the learned embeddings (vectors). Therefore, the capability in preserving graph characteristics including structural aspects and semantics highly depends on the design of the KGE, as well as the inherited abilities from the underlying geometry. Many KGEs use the flat geometry which renders them incapable of preserving complex structures and consequently causes wrong inferences by the models. To address this problem, we propose a neuro differential KGE that embeds nodes of a KG on the trajectories of Ordinary Differential Equations (ODEs). To this end, we represent each relation (edge) in a KG as a vector field on a smooth Riemannian manifold. We specifically parameterize ODEs by a neural network to represent various complex shape manifolds and more importantly complex shape vector fields on the manifold. Therefore, the underlying embedding space is capable of getting various geometric forms to encode complexity in subgraph structures with different motifs. Experiments on synthetic and benchmark dataset as well as social network KGs justify the ODE trajectories as a means to structure preservation and consequently avoiding wrong inferences over state-of-the-art KGE models.

Chengjin Xu, Mojtaba Nayyeri, Fouad Alkhoury et al.

In the last few years, there has been a surge of interest in learning representations of entitiesand relations in knowledge graph (KG). However, the recent availability of temporal knowledgegraphs (TKGs) that contain time information for each fact created the need for reasoning overtime in such TKGs. In this regard, we present a new approach of TKG embedding, TeRo, which defines the temporal evolution of entity embedding as a rotation from the initial time to the currenttime in the complex vector space. Specially, for facts involving time intervals, each relation isrepresented as a pair of dual complex embeddings to handle the beginning and the end of therelation, respectively. We show our proposed model overcomes the limitations of the existing KG embedding models and TKG embedding models and has the ability of learning and inferringvarious relation patterns over time. Experimental results on four different TKGs show that TeRo significantly outperforms existing state-of-the-art models for link prediction. In addition, we analyze the effect of time granularity on link prediction over TKGs, which as far as we know hasnot been investigated in previous literature.

Chengjin Xu, Mojtaba Nayyeri, Yung-Yu Chen et al.

Knowledge graph (KG) embedding aims at embedding entities and relations in a KG into a lowdimensional latent representation space. Existing KG embedding approaches model entities andrelations in a KG by utilizing real-valued , complex-valued, or hypercomplex-valued (Quaternionor Octonion) representations, all of which are subsumed into a geometric algebra. In this work,we introduce a novel geometric algebra-based KG embedding framework, GeomE, which uti-lizes multivector representations and the geometric product to model entities and relations. Ourframework subsumes several state-of-the-art KG embedding approaches and is advantageouswith its ability of modeling various key relation patterns, including (anti-)symmetry, inversionand composition, rich expressiveness with higher degree of freedom as well as good general-ization capacity. Experimental results on multiple benchmark knowledge graphs show that theproposed approach outperforms existing state-of-the-art models for link prediction.

Mikhail Galkin, Priyansh Trivedi, Gaurav Maheshwari et al.

Hyper-relational knowledge graphs (KGs) (e.g., Wikidata) enable associating additional key-value pairs along with the main triple to disambiguate, or restrict the validity of a fact. In this work, we propose a message passing based graph encoder - StarE capable of modeling such hyper-relational KGs. Unlike existing approaches, StarE can encode an arbitrary number of additional information (qualifiers) along with the main triple while keeping the semantic roles of qualifiers and triples intact. We also demonstrate that existing benchmarks for evaluating link prediction (LP) performance on hyper-relational KGs suffer from fundamental flaws and thus develop a new Wikidata-based dataset - WD50K. Our experiments demonstrate that StarE based LP model outperforms existing approaches across multiple benchmarks. We also confirm that leveraging qualifiers is vital for link prediction with gains up to 25 MRR points compared to triple-based representations.

Debayan Banerjee, Debanjan Chaudhuri, Mohnish Dubey et al.

Question Answering systems are generally modelled as a pipeline consisting of a sequence of steps. In such a pipeline, Entity Linking (EL) is often the first step. Several EL models first perform span detection and then entity disambiguation. In such models errors from the span detection phase cascade to later steps and result in a drop of overall accuracy. Moreover, lack of gold entity spans in training data is a limiting factor for span detector training. Hence the movement towards end-to-end EL models began where no separate span detection step is involved. In this work we present a novel approach to end-to-end EL by applying the popular Pointer Network model, which achieves competitive performance. We demonstrate this in our evaluation over three datasets on the Wikidata Knowledge Graph.

Jason Armitage, Shramana Thakur, Rishi Tripathi et al.

We learn about the world from a diverse range of sensory information. Automated systems lack this ability as investigation has centred on processing information presented in a single form. Adapting architectures to learn from multiple modalities creates the potential to learn rich representations of the world - but current multimodal systems only deliver marginal improvements on unimodal approaches. Neural networks learn sampling noise during training with the result that performance on unseen data is degraded. This research introduces a second objective over the multimodal fusion process learned with variational inference. Regularisation methods are implemented in the inner training loop to control variance and the modular structure stabilises performance as additional neurons are added to layers. This framework is evaluated on a multilabel classification task with textual and visual inputs to demonstrate the potential for multiple objectives and probabilistic methods to lower variance and improve generalisation.

Jason Armitage, Endri Kacupaj, Golsa Tahmasebzadeh et al.

In this paper, we introduce the MLM (Multiple Languages and Modalities) dataset - a new resource to train and evaluate multitask systems on samples in multiple modalities and three languages. The generation process and inclusion of semantic data provide a resource that further tests the ability for multitask systems to learn relationships between entities. The dataset is designed for researchers and developers who build applications that perform multiple tasks on data encountered on the web and in digital archives. A second version of MLM provides a geo-representative subset of the data with weighted samples for countries of the European Union. We demonstrate the value of the resource in developing novel applications in the digital humanities with a motivating use case and specify a benchmark set of tasks to retrieve modalities and locate entities in the dataset. Evaluation of baseline multitask and single task systems on the full and geo-representative versions of MLM demonstrate the challenges of generalising on diverse data. In addition to the digital humanities, we expect the resource to contribute to research in multimodal representation learning, location estimation, and scene understanding.

Isaiah Onando Mulang', Kuldeep Singh, Chaitali Prabhu et al.

Pretrained Transformer models have emerged as state-of-the-art approaches that learn contextual information from text to improve the performance of several NLP tasks. These models, albeit powerful, still require specialized knowledge in specific scenarios. In this paper, we argue that context derived from a knowledge graph (in our case: Wikidata) provides enough signals to inform pretrained transformer models and improve their performance for named entity disambiguation (NED) on Wikidata KG. We further hypothesize that our proposed KG context can be standardized for Wikipedia, and we evaluate the impact of KG context on state-of-the-art NED model for the Wikipedia knowledge base. Our empirical results validate that the proposed KG context can be generalized (for Wikipedia), and providing KG context in transformer architectures considerably outperforms the existing baselines, including the vanilla transformer models.

Mehdi Ali, Max Berrendorf, Charles Tapley Hoyt et al.

Recently, knowledge graph embeddings (KGEs) received significant attention, and several software libraries have been developed for training and evaluating KGEs. While each of them addresses specific needs, we re-designed and re-implemented PyKEEN, one of the first KGE libraries, in a community effort. PyKEEN 1.0 enables users to compose knowledge graph embedding models (KGEMs) based on a wide range of interaction models, training approaches, loss functions, and permits the explicit modeling of inverse relations. Besides, an automatic memory optimization has been realized in order to exploit the provided hardware optimally, and through the integration of Optuna extensive hyper-parameter optimization (HPO) functionalities are provided.

Denis Lukovnikov, Jens Lehmann, Asja Fischer

Many popular variants of graph neural networks (GNNs) that are capable of handling multi-relational graphs may suffer from vanishing gradients. In this work, we propose a novel GNN architecture based on the Gated Graph Neural Network with an improved ability to handle long-range dependencies in multi-relational graphs. An experimental analysis on different synthetic tasks demonstrates that the proposed architecture outperforms several popular GNN models.