Kalpa Gunaratna

Kalpa Gunaratna, Vijay Srinivasan, Akhila Yerukola et al.

Joint intent detection and slot filling is a key research topic in natural language understanding (NLU). Existing joint intent and slot filling systems analyze and compute features collectively for all slot types, and importantly, have no way to explain the slot filling model decisions. In this work, we propose a novel approach that: (i) learns to generate additional slot type specific features in order to improve accuracy and (ii) provides explanations for slot filling decisions for the first time in a joint NLU model. We perform an additional constrained supervision using a set of binary classifiers for the slot type specific feature learning, thus ensuring appropriate attention weights are learned in the process to explain slot filling decisions for utterances. Our model is inherently explainable and does not need any post-hoc processing. We evaluate our approach on two widely used datasets and show accuracy improvements. Moreover, a detailed analysis is also provided for the exclusive slot explainability.

Kalpa Gunaratna, Vijay Srinivasan, Hongxia Jin

Joint intent detection and slot filling, which is also termed as joint NLU (Natural Language Understanding) is invaluable for smart voice assistants. Recent advancements in this area have been heavily focusing on improving accuracy using various techniques. Explainability is undoubtedly an important aspect for deep learning-based models including joint NLU models. Without explainability, their decisions are opaque to the outside world and hence, have tendency to lack user trust. Therefore to bridge this gap, we transform the full joint NLU model to be `inherently' explainable at granular levels without compromising on accuracy. Further, as we enable the full joint NLU model explainable, we show that our extension can be successfully used in other general classification tasks. We demonstrate this using sentiment analysis and named entity recognition.

Yash Saxena, Ankur Padia, Mandar S Chaudhary et al.

Traditional Retrieval-Augmented Generation (RAG) pipelines rely on similarity-based retrieval and re-ranking, which depend on heuristics such as top-k, and lack explainability, interpretability, and robustness against adversarial content. To address this gap, we propose a novel method METEORA that replaces re-ranking in RAG with a rationale-driven selection approach. METEORA operates in two stages. First, a general-purpose LLM is preference-tuned to generate rationales conditioned on the input query using direct preference optimization. These rationales guide the evidence chunk selection engine, which selects relevant chunks in three stages: pairing individual rationales with corresponding retrieved chunks for local relevance, global selection with elbow detection for adaptive cutoff, and context expansion via neighboring chunks. This process eliminates the need for top-k heuristics. The rationales are also used for consistency check using a Verifier LLM to detect and filter poisoned or misleading content for safe generation. The framework provides explainable and interpretable evidence flow by using rationales consistently across both selection and verification. Our evaluation across six datasets spanning legal, financial, and academic research domains shows that METEORA improves generation accuracy by 33.34% while using approximately 50% fewer chunks than state-of-the-art re-ranking methods. In adversarial settings, METEORA significantly improves the F1 score from 0.10 to 0.44 over the state-of-the-art perplexity-based defense baseline, demonstrating strong resilience to poisoning attacks. Code available at: https://anonymous.4open.science/r/METEORA-DC46/README.md

Durga Prasad Maram, Kalpa Gunaratna, Vijay Srinivasan et al.

Multi-hop question answering is a challenging task in which language models must reason over multiple steps to reach the correct answer. With the help of Large Language Models and their reasoning capabilities, existing systems are able to think and decompose an input question over multiple steps to analyze, retrieve, and reason. However, training-based approaches for this problem still suffer from LLM hallucinations and incorrect reasoning paths that hinder performance. Hence, we propose PATHFINDER, an approach that: (i) uses Monte Carlo Tree Search to generate training path traces, (ii) improves training data quality by filtering erroneous and lengthy traces using sub-answer recall and LLM-as-a-judge verification, and (iii) reformulates sub-queries to handle failed retrieval cases. By following these steps, we demonstrate that PATHFINDER improves the performance of multi-hop QA over public benchmark datasets.

Lichang Chen, Shiyang Li, Jun Yan et al.

Large language models (LLMs) strengthen instruction-following capability through instruction-finetuning (IFT) on supervised instruction/response data. However, widely used IFT datasets (e.g., Alpaca's 52k data) surprisingly contain many low-quality instances with incorrect or irrelevant responses, which are misleading and detrimental to IFT. In this paper, we propose a simple and effective data selection strategy that automatically identifies and filters out low-quality data using a strong LLM (e.g., ChatGPT). To this end, we introduce AlpaGasus, which is finetuned on only 9k high-quality data filtered from the 52k Alpaca data. AlpaGasus significantly outperforms the original Alpaca as evaluated by GPT-4 on multiple test sets and the controlled human evaluation. Its 13B variant matches $>90\%$ performance of its teacher LLM (i.e., Text-Davinci-003 generating the 52k data) on test tasks. It also provides 5.7x faster training, reducing the training time for a 7B variant from 80 minutes (for Alpaca) to 14 minutes. Moreover, the experiments prove the efficacy of our method across diverse datasets, base models, and LLM filters. Overall, AlpaGasus demonstrates a novel data-centric IFT paradigm that can be generally applied to instruction-tuning data, leading to faster training and better instruction-following models. Our project page is available at: https://lichang-chen.github.io/AlpaGasus/

Manas Gaur, Kalpa Gunaratna, Vijay Srinivasan et al.

Conversational Information Seeking (CIS) is a relatively new research area within conversational AI that attempts to seek information from end-users in order to understand and satisfy users' needs. If realized, such a system has far-reaching benefits in the real world; for example, a CIS system can assist clinicians in pre-screening or triaging patients in healthcare. A key open sub-problem in CIS that remains unaddressed in the literature is generating Information Seeking Questions (ISQs) based on a short initial query from the end-user. To address this open problem, we propose Information SEEking Question generator (ISEEQ), a novel approach for generating ISQs from just a short user query, given a large text corpus relevant to the user query. Firstly, ISEEQ uses a knowledge graph to enrich the user query. Secondly, ISEEQ uses the knowledge-enriched query to retrieve relevant context passages to ask coherent ISQs adhering to a conceptual flow. Thirdly, ISEEQ introduces a new deep generative-adversarial reinforcement learning-based approach for generating ISQs. We show that ISEEQ can generate high-quality ISQs to promote the development of CIS agents. ISEEQ significantly outperforms comparable baselines on five ISQ evaluation metrics across four datasets having user queries from diverse domains. Further, we argue that ISEEQ is transferable across domains for generating ISQs, as it shows the acceptable performance when trained and tested on different pairs of domains. The qualitative human evaluation confirms ISEEQ-generated ISQs are comparable in quality to human-generated questions and outperform the best comparable baseline.

Kalpa Gunaratna, Vijay Srinivasan, Sandeep Nama et al.

Information Extraction from visual documents enables convenient and intelligent assistance to end users. We present a Neighborhood-based Information Extraction (NIE) approach that uses contextual language models and pays attention to the local neighborhood context in the visual documents to improve information extraction accuracy. We collect two different visual document datasets and show that our approach outperforms the state-of-the-art global context-based IE technique. In fact, NIE outperforms existing approaches in both small and large model sizes. Our on-device implementation of NIE on a mobile platform that generally requires small models showcases NIE's usefulness in practical real-world applications.

Kalpa Gunaratna, Yu Wang, Hongxia Jin

Knowledge is captured in the form of entities and their relationships and stored in knowledge graphs. Knowledge graphs enhance the capabilities of applications in many different areas including Web search, recommendation, and natural language understanding. This is mainly because, entities enable machines to understand things that go beyond simple tokens. Many modern algorithms use learned entity embeddings from these structured representations. However, building a knowledge graph takes time and effort, hence very costly and nontrivial. On the other hand, many Web sources describe entities in some structured format and therefore, finding ways to get them into useful entity knowledge is advantageous. We propose an approach that processes entity centric textual knowledge sources to learn entity embeddings and in turn avoids the need for a traditional knowledge graph. We first extract triples into the new representation format that does not use traditional complex triple extraction methods defined by pre-determined relationship labels. Then we learn entity embeddings through this new type of triples. We show that the embeddings learned from our approach are: (i) high quality and comparable to a known knowledge graph-based embeddings and can be used to improve them further, (ii) better than a contextual language model-based entity embeddings, and (iii) easy to compute and versatile in domain-specific applications where a knowledge graph is not readily available

Kechen Qin, Yu Wang, Cheng Li et al.

Multi-hop knowledge based question answering (KBQA) is a complex task for natural language understanding. Many KBQA approaches have been proposed in recent years, and most of them are trained based on labeled reasoning path. This hinders the system's performance as many correct reasoning paths are not labeled as ground truth, and thus they cannot be learned. In this paper, we introduce an end-to-end KBQA system which can leverage multiple reasoning paths' information and only requires labeled answer as supervision. We conduct experiments on several benchmark datasets containing both single-hop simple questions as well as muti-hop complex questions, including WebQuestionSP (WQSP), ComplexWebQuestion-1.1 (CWQ), and PathQuestion-Large (PQL), and demonstrate strong performance.

Shuxin Li, Zixian Huang, Gong Cheng et al.

A prominent application of knowledge graph (KG) is document enrichment. Existing methods identify mentions of entities in a background KG and enrich documents with entity types and direct relations. We compute an entity relation subgraph (ERG) that can more expressively represent indirect relations among a set of mentioned entities. To find compact, representative, and relevant ERGs for effective enrichment, we propose an efficient best-first search algorithm to solve a new combinatorial optimization problem that achieves a trade-off between representativeness and compactness, and then we exploit ontological knowledge to rank ERGs by entity-based document-KG and intra-KG relevance. Extensive experiments and user studies show the promising performance of our approach.

Junyou Li, Gong Cheng, Qingxia Liu et al.

In a large-scale knowledge graph (KG), an entity is often described by a large number of triple-structured facts. Many applications require abridged versions of entity descriptions, called entity summaries. Existing solutions to entity summarization are mainly unsupervised. In this paper, we present a supervised approach NEST that is based on our novel neural model to jointly encode graph structure and text in KGs and generate high-quality diversified summaries. Since it is costly to obtain manually labeled summaries for training, our supervision is weak as we train with programmatically labeled data which may contain noise but is free of manual work. Evaluation results show that our approach significantly outperforms the state of the art on two public benchmarks.

Qingxia Liu, Gong Cheng, Kalpa Gunaratna et al.

Entity summarization is the problem of computing an optimal compact summary for an entity by selecting a size-constrained subset of triples from RDF data. Entity summarization supports a multiplicity of applications and has led to fruitful research. However, there is a lack of evaluation efforts that cover the broad spectrum of existing systems. One reason is a lack of benchmarks for evaluation. Some benchmarks are no longer available, while others are small and have limitations. In this paper, we create an Entity Summarization BenchMark (ESBM) which overcomes the limitations of existing benchmarks and meets standard desiderata for a benchmark. Using this largest available benchmark for evaluating general-purpose entity summarizers, we perform the most extensive experiment to date where 9~existing systems are compared. Considering that all of these systems are unsupervised, we also implement and evaluate a supervised learning based system for reference.

Qingxia Liu, Gong Cheng, Kalpa Gunaratna et al.

The increasing availability of semantic data has substantially enhanced Web applications. Semantic data such as RDF data is commonly represented as entity-property-value triples. The magnitude of semantic data, in particular the large number of triples describing an entity, could overload users with excessive amounts of information. This has motivated fruitful research on automated generation of summaries for entity descriptions to satisfy users' information needs efficiently and effectively. We focus on this prominent topic of entity summarization, and our research objective is to present the first comprehensive survey of entity summarization research. Rather than separately reviewing each method, our contributions include (1) identifying and classifying technical features of existing methods to form a high-level overview, (2) identifying and classifying frameworks for combining multiple technical features adopted by existing methods, (3) collecting known benchmarks for intrinsic evaluation and efforts for extrinsic evaluation, and (4) suggesting research directions for future work. By investigating the literature, we synthesized two hierarchies of techniques. The first hierarchy categories generic technical features into several perspectives: frequency and centrality, informativeness, and diversity and coverage. In the second hierarchy we present domain-specific and task-specific technical features, including the use of domain knowledge, context awareness, and personalization. Our review demonstrated that existing methods are mainly unsupervised and they combine multiple technical features using various frameworks: random surfer models, similarity-based grouping, MMR-like re-ranking, or combinatorial optimization. We also found a few deep learning based methods in recent research.

Kalpa Gunaratna

Document retrieval has been an important research problem over many years in the information retrieval community. State-of-the-art techniques utilize various methods in matching documents to a given document including keywords, phrases, and annotations. In this paper, we propose a new approach for document retrieval that utilizes predications (subject-predicate-object triples) extracted from the documents. We represent documents as sets of predications. We measure the similarity between predications to compute the similarity between documents. Our approach utilizes the hierarchical information available in ontologies in computing concept-concept similarity, making the approach flexible. Predication-based document similarity is more precise and forms the basis for a semantically aware document retrieval system. We show that the approach is competitive with an existing state-of-the-art related document retrieval technique in the biomedical domain.