Radu Florian

Young-Suk Lee, Md Arafat Sultan, Yousef El-Kurdi et al. · ibm-research

Using in-context learning (ICL) for data generation, techniques such as Self-Instruct (Wang et al., 2023) or the follow-up Alpaca (Taori et al., 2023) can train strong conversational agents with only a small amount of human supervision. One limitation of these approaches is that they resort to very large language models (around 175B parameters) that are also proprietary and non-public. Here we explore the application of such techniques to language models that are much smaller (around 10B--40B parameters) and have permissive licenses. We find the Self-Instruct approach to be less effective at these sizes and propose new ICL methods that draw on two main ideas: (a) Categorization and simplification of the ICL templates to make prompt learning easier for the LM, and (b) Ensembling over multiple LM outputs to help select high-quality synthetic examples. Our algorithm leverages the 175 Self-Instruct seed tasks and employs separate pipelines for instructions that require an input and instructions that do not. Empirical investigations with different LMs show that: (1) Our proposed method yields higher-quality instruction tuning data than Self-Instruct, (2) It improves performances of both vanilla and instruction-tuned LMs by significant margins, and (3) Smaller instruction-tuned LMs generate more useful outputs than their larger un-tuned counterparts. Our codebase is available at https://github.com/IBM/ensemble-instruct.

Avirup Sil, Jaydeep Sen, Bhavani Iyer et al. · ibm-research

The field of Question Answering (QA) has made remarkable progress in recent years, thanks to the advent of large pre-trained language models, newer realistic benchmark datasets with leaderboards, and novel algorithms for key components such as retrievers and readers. In this paper, we introduce PRIMEQA: a one-stop and open-source QA repository with an aim to democratize QA re-search and facilitate easy replication of state-of-the-art (SOTA) QA methods. PRIMEQA supports core QA functionalities like retrieval and reading comprehension as well as auxiliary capabilities such as question generation.It has been designed as an end-to-end toolkit for various use cases: building front-end applications, replicating SOTA methods on pub-lic benchmarks, and expanding pre-existing methods. PRIMEQA is available at : https://github.com/primeqa.

Andrew Drozdov, Jiawei Zhou, Radu Florian et al. · harvard, ibm-research

Transition-based parsers for Abstract Meaning Representation (AMR) rely on node-to-word alignments. These alignments are learned separately from parser training and require a complex pipeline of rule-based components, pre-processing, and post-processing to satisfy domain-specific constraints. Parsers also train on a point-estimate of the alignment pipeline, neglecting the uncertainty due to the inherent ambiguity of alignment. In this work we explore two avenues for overcoming these limitations. First, we propose a neural aligner for AMR that learns node-to-word alignments without relying on complex pipelines. We subsequently explore a tighter integration of aligner and parser training by considering a distribution over oracle action sequences arising from aligner uncertainty. Empirical results show this approach leads to more accurate alignments and generalization better from the AMR2.0 to AMR3.0 corpora. We attain a new state-of-the art for gold-only trained models, matching silver-trained performance without the need for beam search on AMR3.0.

Jon Saad-Falcon, Omar Khattab, Keshav Santhanam et al. · ibm-research

Many information retrieval tasks require large labeled datasets for fine-tuning. However, such datasets are often unavailable, and their utility for real-world applications can diminish quickly due to domain shifts. To address this challenge, we develop and motivate a method for using large language models (LLMs) to generate large numbers of synthetic queries cheaply. The method begins by generating a small number of synthetic queries using an expensive LLM. After that, a much less expensive one is used to create large numbers of synthetic queries, which are used to fine-tune a family of reranker models. These rerankers are then distilled into a single efficient retriever for use in the target domain. We show that this technique boosts zero-shot accuracy in long-tail domains and achieves substantially lower latency than standard reranking methods.

Revanth Gangi Reddy, Bhavani Iyer, Md Arafat Sultan et al. · amazon-science, ibm-research

Neural passage retrieval is a new and promising approach in open retrieval question answering. In this work, we stress-test the Dense Passage Retriever (DPR) -- a state-of-the-art (SOTA) open domain neural retrieval model -- on closed and specialized target domains such as COVID-19, and find that it lags behind standard BM25 in this important real-world setting. To make DPR more robust under domain shift, we explore its fine-tuning with synthetic training examples, which we generate from unlabeled target domain text using a text-to-text generator. In our experiments, this noisy but fully automated target domain supervision gives DPR a sizable advantage over BM25 in out-of-domain settings, making it a more viable model in practice. Finally, an ensemble of BM25 and our improved DPR model yields the best results, further pushing the SOTA for open retrieval QA on multiple out-of-domain test sets.

Keshav Santhanam, Jon Saad-Falcon, Martin Franz et al. · ibm-research

Neural information retrieval (IR) systems have progressed rapidly in recent years, in large part due to the release of publicly available benchmarking tasks. Unfortunately, some dimensions of this progress are illusory: the majority of the popular IR benchmarks today focus exclusively on downstream task accuracy and thus conceal the costs incurred by systems that trade away efficiency for quality. Latency, hardware cost, and other efficiency considerations are paramount to the deployment of IR systems in user-facing settings. We propose that IR benchmarks structure their evaluation methodology to include not only metrics of accuracy, but also efficiency considerations such as a query latency and the corresponding cost budget for a reproducible hardware setting. For the popular IR benchmarks MS MARCO and XOR-TyDi, we show how the best choice of IR system varies according to how these efficiency considerations are chosen and weighed. We hope that future benchmarks will adopt these guidelines toward more holistic IR evaluation.

Young-Suk Lee, Ramón Fernandez Astudillo, Radu Florian et al. · ibm-research

Instruction fine-tuned language models on a collection of instruction annotated datasets (FLAN) have shown highly effective to improve model performance and generalization to unseen tasks. However, a majority of standard parsing tasks including abstract meaning representation (AMR), universal dependency (UD), semantic role labeling (SRL) has been excluded from the FLAN collections for both model training and evaluations. In this paper, we take one of such instruction fine-tuned pre-trained language models, i.e. FLAN-T5, and fine-tune them for AMR parsing. Our extensive experiments on various AMR parsing tasks including AMR2.0, AMR3.0 and BioAMR indicate that FLAN-T5 fine-tuned models out-perform previous state-of-the-art models across all tasks. In addition, full fine-tuning followed by the parameter efficient fine-tuning, LoRA, further improves the model performances, setting new state-of-the-arts in Smatch on AMR2.0 (86.4), AMR3.0 (84.9) and BioAMR (82.3).

Md Arafat Sultan, Avirup Sil, Radu Florian · ibm-research

Machine learning models are prone to overfitting their training (source) domains, which is commonly believed to be the reason why they falter in novel target domains. Here we examine the contrasting view that multi-source domain generalization (DG) is first and foremost a problem of mitigating source domain underfitting: models not adequately learning the signal already present in their multi-domain training data. Experiments on a reading comprehension DG benchmark show that as a model learns its source domains better -- using familiar methods such as knowledge distillation (KD) from a bigger model -- its zero-shot out-of-domain utility improves at an even faster pace. Improved source domain learning also demonstrates superior out-of-domain generalization over three popular existing DG approaches that aim to limit overfitting. Our implementation of KD-based domain generalization is available via PrimeQA at: https://ibm.biz/domain-generalization-with-kd.

Scott McCarley, Mihaela Bornea, Sara Rosenthal et al. · ibm-research

Recent machine reading comprehension datasets include extractive and boolean questions but current approaches do not offer integrated support for answering both question types. We present a multilingual machine reading comprehension system and front-end demo that handles boolean questions by providing both a YES/NO answer and highlighting supporting evidence, and handles extractive questions by highlighting the answer in the passage. Our system, GAAMA 2.0, is ranked first on the Tydi QA leaderboard at the time of this writing. We contrast two different implementations of our approach. The first includes several independent stacks of transformers allowing easy deployment of each component. The second is a single stack of transformers utilizing adapters to reduce GPU memory footprint in a resource-constrained environment.

Parul Awasthy, Aashka Trivedi, Yushu Yang et al.

We introduce the multilingual Granite Embedding R2 models, a family of encoder-based embedding models for enterprise-scale dense retrieval across 200+ languages. Extending our English-focused R2 release, these models add enhanced support for 52 languages and programming code, a 32,768-token context window (a 64x expansion over R1), and state-of-the-art overall performance across multilingual and cross-lingual text search, code retrieval, long-document search, and reasoning retrieval datasets. The release consists of two bi-encoder models based on the ModernBERT architecture with an expanded multilingual vocabulary: a 311M-parameter full-size, and a 97M-parameter compact model built via model pruning and vocabulary selection that achieves the highest retrieval score of any open multilingual embedding model under 100M parameters. The full-size also supports Matryoshka Representation Learning for flexible embedding dimensionality. Both models are trained on enterprise-appropriate data with governance oversight, and released under the Apache 2.0 license at https://huggingface.co/collections/ibm-granite, designed to support responsible use and enable unrestricted research and enterprise adoption.

Malik H. Altakrori, Nizar Habash, Abdelhakim Freihat et al.

We present DialectalArabicMMLU, a new benchmark for evaluating the performance of large language models (LLMs) across Arabic dialects. While recently developed Arabic and multilingual benchmarks have advanced LLM evaluation for Modern Standard Arabic (MSA), dialectal varieties remain underrepresented despite their prevalence in everyday communication. DialectalArabicMMLU extends the MMLU-Redux framework through manual translation and adaptation of 3K multiple-choice question-answer pairs into five major dialects (Syrian, Egyptian, Emirati, Saudi, and Moroccan), yielding a total of 15K QA pairs across 32 academic and professional domains (22K QA pairs when also including English and MSA). The benchmark enables systematic assessment of LLM reasoning and comprehension beyond MSA, supporting both task-based and linguistic analysis. We evaluate 19 open-weight Arabic and multilingual LLMs (1B-13B parameters) and report substantial performance variation across dialects, revealing persistent gaps in dialectal generalization. DialectalArabicMMLU provides the first unified, human-curated resource for measuring dialectal understanding in Arabic, thus promoting more inclusive evaluation and future model development.

Sara Rosenthal, Avirup Sil, Radu Florian et al.

Retrieval Augmented Generation (RAG) has become a popular application for large language models. It is preferable that successful RAG systems provide accurate answers that are supported by being grounded in a passage without any hallucinations. While considerable work is required for building a full RAG pipeline, being able to benchmark performance is also necessary. We present ClapNQ, a benchmark Long-form Question Answering dataset for the full RAG pipeline. ClapNQ includes long answers with grounded gold passages from Natural Questions (NQ) and a corpus to perform either retrieval, generation, or the full RAG pipeline. The ClapNQ answers are concise, 3x smaller than the full passage, and cohesive, meaning that the answer is composed fluently, often by integrating multiple pieces of the passage that are not contiguous. RAG models must adapt to these properties to be successful at ClapNQ. We present baseline experiments and analysis for ClapNQ that highlight areas where there is still significant room for improvement in grounded RAG. CLAPNQ is publicly available at https://github.com/primeqa/clapnq

Young-Suk Lee, Chulaka Gunasekara, Danish Contractor et al.

We introduce a technique for multi-document grounded multi-turn synthetic dialog generation that incorporates three main ideas. First, we control the overall dialog flow using taxonomy-driven user queries that are generated with Chain-of-Thought (CoT) prompting. Second, we support the generation of multi-document grounded dialogs by mimicking real-world use of retrievers to update the grounding documents after every user-turn in the dialog. Third, we apply LLM-as-a-Judge to filter out queries with incorrect answers. Human evaluation of the synthetic dialog data suggests that the data is diverse, coherent, and includes mostly correct answers. Both human and automatic evaluations of answerable queries indicate that models fine-tuned on synthetic dialogs consistently out-perform those fine-tuned on existing human generated training data across four publicly available multi-turn document grounded benchmark test sets.

Keshav Ramji, Young-Suk Lee, Ramón Fernandez Astudillo et al.

It is often desirable for Large Language Models (LLMs) to capture multiple objectives when providing a response. In document-grounded response generation, for example, agent responses are expected to be relevant to a user's query while also being grounded in a given document. In this paper, we introduce Proxy Metric-based Self-Refinement (ProMiSe), which enables an LLM to refine its own initial response along key dimensions of quality guided by external metrics feedback, yielding an overall better final response. ProMiSe leverages feedback on response quality through principle-specific proxy metrics, and iteratively refines its response one principle at a time. We apply ProMiSe to open source language models Flan-T5-XXL and Llama-2-13B-Chat, to evaluate its performance on document-grounded question answering datasets, MultiDoc2Dial and QuAC, demonstrating that self-refinement improves response quality. We further show that fine-tuning Llama-2-13B-Chat on the synthetic dialogue data generated by ProMiSe yields significant performance improvements over the zero-shot baseline as well as a supervised fine-tuned model on human annotated data.

Parul Awasthy, Aashka Trivedi, Yulong Li et al. · ibm-research

We introduce the Granite Embedding models, a family of encoder-based embedding models designed for retrieval tasks, spanning dense-retrieval and sparse retrieval architectures, with both English and Multilingual capabilities. This report provides the technical details of training these highly effective 12 layer embedding models, along with their efficient 6 layer distilled counterparts. Extensive evaluations show that the models, developed with techniques like retrieval oriented pretraining, contrastive finetuning, knowledge distillation, and model merging significantly outperform publicly available models of similar sizes on both internal IBM retrieval and search tasks, and have equivalent performance on widely used information retrieval benchmarks, while being trained on high-quality data suitable for enterprise use. We publicly release all our Granite Embedding models under the Apache 2.0 license, allowing both research and commercial use at https://huggingface.co/collections/ibm-granite.

Parul Awasthy, Aashka Trivedi, Yulong Li et al. · ibm-research

We introduce the Granite Embedding R2 models, a comprehensive family of high-performance English encoder-based embedding models engineered for enterprise-scale dense retrieval applications. Building upon our first-generation release, these models deliver substantial improvements, including 16x expanded context length (8,192 tokens), state-of-the-art performance across diverse retrieval domains - text, code, long-document search, multi-turn conversational, and tabular data - and measurable speed advantages of 19-44\% over leading competitors while maintaining superior accuracy. Our release encompasses both bi-encoder and cross-encoder architectures, featuring a highly effective 22-layer retriever model and its efficient 12-layer counterpart, alongside a high-quality reranker model, all trained exclusively on enterprise-appropriate data with comprehensive governance oversight. The models demonstrate exceptional versatility across standard benchmarks, IBM-developed evaluation suites, and real-world enterprise use cases, establishing new performance standards for open-source embedding models. In an era where retrieval speed and accuracy are paramount for competitive advantage, the Granite R2 models deliver a compelling combination of cutting-edge performance, enterprise-ready licensing, and transparent data provenance that organizations require for mission-critical deployments. All models are publicly available under the Apache 2.0 license at https://huggingface.co/collections/ibm-granite, enabling unrestricted research and commercial use.

Ramón Fernandez Astudillo, Md Arafat Sultan, Aashka Trivedi et al.

Inference scaling helps LLMs solve complex reasoning problems through extended runtime computation. On top of long chain-of-thought (long-CoT) models, purely inference-time techniques such as best-of-N (BoN) sampling, majority voting, or more generally, minimum Bayes risk decoding (MBRD), can further improve LLM accuracy by generating multiple candidate solutions and aggregating over them. These methods typically leverage additional signals in the form of reward models and risk/similarity functions that compare generated samples, e.g., exact match in some normalized space or standard similarity metrics such as Rouge. Here we present a novel method for incorporating reward and risk/similarity signals into MBRD. Based on the concept of optimal policy in KL-controlled reinforcement learning, our framework provides a simple and well-defined mechanism for leveraging such signals, offering several advantages over traditional inference-time methods: higher robustness, improved accuracy, and well-understood asymptotic behavior. In addition, it allows for the development of a sample-efficient variant of MBRD that can adjust the number of samples to generate according to the difficulty of the problem, without relying on majority vote counts. We empirically demonstrate the advantages of our approach on math (MATH-$500$) and coding (HumanEval) tasks using recent open-source models. We also present a comprehensive analysis of its accuracy-compute trade-offs.

Meet Doshi, Aashka Trivedi, Vishwajeet Kumar et al.

Representation learning is central to many downstream tasks such as search, clustering, classification, and reranking. State-of-the-art sequence encoders typically collapse a variable-length token sequence to a single vector using a pooling operator, most commonly a special [CLS] token or mean pooling over token embeddings. In this paper, we identify systematic weaknesses of these pooling strategies: [CLS] tends to concentrate information toward the initial positions of the sequence and can under-represent distributed evidence, while mean pooling can dilute salient local signals, sometimes leading to worse short-context performance. To address these issues, we introduce Landmark (LMK) pooling, which partitions a sequence into chunks, inserts landmark tokens between chunks, and forms the final representation by mean-pooling the landmark token embeddings. This simple mechanism improves long-context extrapolation without sacrificing local salient features, at the cost of introducing a small number of special tokens. We empirically demonstrate that LMK pooling matches existing methods on short-context retrieval tasks and yields substantial improvements on long-context tasks, making it a practical and scalable alternative to existing pooling methods.

Young-Suk Lee, Ramon Fernandez Astudillo, Radu Florian

Deep research agents increasingly interleave web browsing with multi-step computation, yet existing benchmarks evaluate these capabilities in isolation, creating a blind spot in assessing real-world performance. We introduce DRBENCHER, a synthetic benchmark generator for questions that require both browsing and computation. It enforces four criteria: verifiability (gold answers are computed by executing parameterized code over knowledge-graph values), complexity (multi-hop entity identification, property retrieval, and domain-specific computation), difficulty (a two-stage verification cascade filters out questions solvable by the generating model), and diversity (a greedy max-min embedding filter maximizes coverage). These criteria are realized via a unified answer-first pipeline spanning five domains: biochemistry, financial, geophysical, security, and history. Human evaluation shows 76% validity (84% excluding stale data), with 35% of errors due to outdated knowledge-graph entries, highlighting an inherent limitation of systems that reason over evolving data. Automatic evaluation shows that the strongest frontier model achieves only 20% answer accuracy. Compared to manually constructed benchmarks (BrowseComp+, MATH-500, GPQA), DRBENCHER achieves the highest semantic diversity.

Jasper Xian, Saron Samuel, Faraz Khoubsirat et al.

We develop a method for training small-scale (under 100M parameter) neural information retrieval models with as few as 10 gold relevance labels. The method depends on generating synthetic queries for documents using a language model (LM), and the key step is that we automatically optimize the LM prompt that is used to generate these queries based on training quality. In experiments with the BIRCO benchmark, we find that models trained with our method outperform RankZephyr and are competitive with RankLLama, both of which are 7B parameter models trained on over 100K labels. These findings point to the power of automatic prompt optimization for synthetic dataset generation.

Teresa Lynn, Malik H. Altakrori, Samar Mohamed Magdy et al.

The rapid evolution of Natural Language Processing (NLP) has favoured major languages such as English, leaving a significant gap for many others due to limited resources. This is especially evident in the context of data annotation, a task whose importance cannot be underestimated, but which is time-consuming and costly. Thus, any dataset for resource-poor languages is precious, in particular when it is task-specific. Here, we explore the feasibility of repurposing an existing multilingual dataset for a new NLP task: we repurpose a subset of the BELEBELE dataset (Bandarkar et al., 2023), which was designed for multiple-choice question answering (MCQA), to enable the more practical task of extractive QA (EQA) in the style of machine reading comprehension. We present annotation guidelines and a parallel EQA dataset for English and Modern Standard Arabic (MSA). We also present QA evaluation results for several monolingual and cross-lingual QA pairs including English, MSA, and five Arabic dialects. We aim to help others adapt our approach for the remaining 120 BELEBELE language variants, many of which are deemed under-resourced. We also provide a thorough analysis and share insights to deepen understanding of the challenges and opportunities in NLP task reformulation.

Sadhana Kumaravel, Tahira Naseem, Ramon Fernandez Astudillo et al.

The sliding window approach provides an elegant way to handle contexts of sizes larger than the Transformer's input window, for tasks like language modeling. Here we extend this approach to the sequence-to-sequence task of document parsing. For this, we exploit recent progress in transition-based parsing to implement a parser with synchronous sliding windows over source and target. We develop an oracle and a parser for document-level AMR by expanding on Structured-BART such that it leverages source-target alignments and constrains decoding to guarantee synchronicity and consistency across overlapping windows. We evaluate our oracle and parser using the Abstract Meaning Representation (AMR) parsing 3.0 corpus. On the Multi-Sentence development set of AMR 3.0, we show that our transition oracle loses only 8\% of the gold cross-sentential links despite using a sliding window. In practice, this approach also results in a high-quality document-level parser with manageable memory requirements. Our proposed system performs on par with the state-of-the-art pipeline approach for document-level AMR parsing task on Multi-Sentence AMR 3.0 corpus while maintaining sentence-level parsing performance.

Jian Ni, Gaetano Rossiello, Alfio Gliozzo et al.

Relation extraction (RE) is an important information extraction task which provides essential information to many NLP applications such as knowledge base population and question answering. In this paper, we present a novel generative model for relation extraction and classification (which we call GREC), where RE is modeled as a sequence-to-sequence generation task. We explore various encoding representations for the source and target sequences, and design effective schemes that enable GREC to achieve state-of-the-art performance on three benchmark RE datasets. In addition, we introduce negative sampling and decoding scaling techniques which provide a flexible tool to tune the precision and recall performance of the model. Our approach can be extended to extract all relation triples from a sentence in one pass. Although the one-pass approach incurs certain performance loss, it is much more computationally efficient.

Tahira Naseem, Austin Blodgett, Sadhana Kumaravel et al.

Despite extensive research on parsing of English sentences into Abstraction Meaning Representation (AMR) graphs, which are compared to gold graphs via the Smatch metric, full-document parsing into a unified graph representation lacks well-defined representation and evaluation. Taking advantage of a super-sentential level of coreference annotation from previous work, we introduce a simple algorithm for deriving a unified graph representation, avoiding the pitfalls of information loss from over-merging and lack of coherence from under-merging. Next, we describe improvements to the Smatch metric to make it tractable for comparing document-level graphs, and use it to re-evaluate the best published document-level AMR parser. We also present a pipeline approach combining the top performing AMR parser and coreference resolution systems, providing a strong baseline for future research.

Mihaela Bornea, Ramon Fernandez Astudillo, Tahira Naseem et al.

We propose a transition-based system to transpile Abstract Meaning Representation (AMR) into SPARQL for Knowledge Base Question Answering (KBQA). This allows us to delegate part of the semantic representation to a strongly pre-trained semantic parser, while learning transpiling with small amount of paired data. We depart from recent work relating AMR and SPARQL constructs, but rather than applying a set of rules, we teach a BART model to selectively use these relations. Further, we avoid explicitly encoding AMR but rather encode the parser state in the attention mechanism of BART, following recent semantic parsing works. The resulting model is simple, provides supporting text for its decisions, and outperforms recent approaches in KBQA across two knowledge bases: DBPedia (LC-QuAD 1.0, QALD-9) and Wikidata (WebQSP, SWQ-WD).

Young-Suk Lee, Ramon Fernandez Astudillo, Thanh Lam Hoang et al.

AMR parsing has experienced an unprecendented increase in performance in the last three years, due to a mixture of effects including architecture improvements and transfer learning. Self-learning techniques have also played a role in pushing performance forward. However, for most recent high performant parsers, the effect of self-learning and silver data augmentation seems to be fading. In this paper we propose to overcome this diminishing returns of silver data by combining Smatch-based ensembling techniques with ensemble distillation. In an extensive experimental setup, we push single model English parser performance to a new state-of-the-art, 85.9 (AMR2.0) and 84.3 (AMR3.0), and return to substantial gains from silver data augmentation. We also attain a new state-of-the-art for cross-lingual AMR parsing for Chinese, German, Italian and Spanish. Finally we explore the impact of the proposed technique on domain adaptation, and show that it can produce gains rivaling those of human annotated data for QALD-9 and achieve a new state-of-the-art for BioAMR.

Sara Rosenthal, Mihaela Bornea, Avirup Sil et al.

Existing datasets that contain boolean questions, such as BoolQ and TYDI QA , provide the user with a YES/NO response to the question. However, a one word response is not sufficient for an explainable system. We promote explainability by releasing a new set of annotations marking the evidence in existing TyDi QA and BoolQ datasets. We show that our annotations can be used to train a model that extracts improved evidence spans compared to models that rely on existing resources. We confirm our findings with a user study which shows that our extracted evidence spans enhance the user experience. We also provide further insight into the challenges of answering boolean questions, such as passages containing conflicting YES and NO answers, and varying degrees of relevance of the predicted evidence.

Jiawei Zhou, Tahira Naseem, Ramón Fernandez Astudillo et al.

Predicting linearized Abstract Meaning Representation (AMR) graphs using pre-trained sequence-to-sequence Transformer models has recently led to large improvements on AMR parsing benchmarks. These parsers are simple and avoid explicit modeling of structure but lack desirable properties such as graph well-formedness guarantees or built-in graph-sentence alignments. In this work we explore the integration of general pre-trained sequence-to-sequence language models and a structure-aware transition-based approach. We depart from a pointer-based transition system and propose a simplified transition set, designed to better exploit pre-trained language models for structured fine-tuning. We also explore modeling the parser state within the pre-trained encoder-decoder architecture and different vocabulary strategies for the same purpose. We provide a detailed comparison with recent progress in AMR parsing and show that the proposed parser retains the desirable properties of previous transition-based approaches, while being simpler and reaching the new parsing state of the art for AMR 2.0, without the need for graph re-categorization.

Haoyang Wen, Anthony Ferritto, Heng Ji et al.

Existing models on Machine Reading Comprehension (MRC) require complex model architecture for effectively modeling long texts with paragraph representation and classification, thereby making inference computationally inefficient for production use. In this work, we propose VAULT: a light-weight and parallel-efficient paragraph representation for MRC based on contextualized representation from long document input, trained using a new Gaussian distribution-based objective that pays close attention to the partially correct instances that are close to the ground-truth. We validate our VAULT architecture showing experimental results on two benchmark MRC datasets that require long context modeling; one Wikipedia-based (Natural Questions (NQ)) and the other on TechNotes (TechQA). VAULT can achieve comparable performance on NQ with a state-of-the-art (SOTA) complex document modeling approach while being 16 times faster, demonstrating the efficiency of our proposed model. We also demonstrate that our model can also be effectively adapted to a completely different domain -- TechQA -- with large improvement over a model fine-tuned on a previously published large PLM.

Jiawei Zhou, Tahira Naseem, Ramón Fernandez Astudillo et al.

Abstract Meaning Representation parsing is a sentence-to-graph prediction task where target nodes are not explicitly aligned to sentence tokens. However, since graph nodes are semantically based on one or more sentence tokens, implicit alignments can be derived. Transition-based parsers operate over the sentence from left to right, capturing this inductive bias via alignments at the cost of limited expressiveness. In this work, we propose a transition-based system that combines hard-attention over sentences with a target-side action pointer mechanism to decouple source tokens from node representations and address alignments. We model the transitions as well as the pointer mechanism through straightforward modifications within a single Transformer architecture. Parser state and graph structure information are efficiently encoded using attention heads. We show that our action-pointer approach leads to increased expressiveness and attains large gains (+1.6 points) against the best transition-based AMR parser in very similar conditions. While using no graph re-categorization, our single model yields the second best Smatch score on AMR 2.0 (81.8), which is further improved to 83.4 with silver data and ensemble decoding.

Janaki Sheth, Young-Suk Lee, Ramon Fernandez Astudillo et al.

We develop high performance multilingualAbstract Meaning Representation (AMR) sys-tems by projecting English AMR annotationsto other languages with weak supervision. Weachieve this goal by bootstrapping transformer-based multilingual word embeddings, in partic-ular those from cross-lingual RoBERTa (XLM-R large). We develop a novel technique forforeign-text-to-English AMR alignment, usingthe contextual word alignment between En-glish and foreign language tokens. This wordalignment is weakly supervised and relies onthe contextualized XLM-R word embeddings.We achieve a highly competitive performancethat surpasses the best published results forGerman, Italian, Spanish and Chinese.

Mihaela Bornea, Lin Pan, Sara Rosenthal et al.

Prior work on multilingual question answering has mostly focused on using large multilingual pre-trained language models (LM) to perform zero-shot language-wise learning: train a QA model on English and test on other languages. In this work, we explore strategies that improve cross-lingual transfer by bringing the multilingual embeddings closer in the semantic space. Our first strategy augments the original English training data with machine translation-generated data. This results in a corpus of multilingual silver-labeled QA pairs that is 14 times larger than the original training set. In addition, we propose two novel strategies, language adversarial training and language arbitration framework, which significantly improve the (zero-resource) cross-lingual transfer performance and result in LM embeddings that are less language-variant. Empirically, we show that the proposed models outperform the previous zero-shot baseline on the recently introduced multilingual MLQA and TyDiQA datasets.

Revanth Gangi Reddy, Bhavani Iyer, Md Arafat Sultan et al.

End-to-end question answering (QA) requires both information retrieval (IR) over a large document collection and machine reading comprehension (MRC) on the retrieved passages. Recent work has successfully trained neural IR systems using only supervised question answering (QA) examples from open-domain datasets. However, despite impressive performance on Wikipedia, neural IR lags behind traditional term matching approaches such as BM25 in more specific and specialized target domains such as COVID-19. Furthermore, given little or no labeled data, effective adaptation of QA systems can also be challenging in such target domains. In this work, we explore the application of synthetically generated QA examples to improve performance on closed-domain retrieval and MRC. We combine our neural IR and MRC systems and show significant improvements in end-to-end QA on the CORD-19 collection over a state-of-the-art open-domain QA baseline.

Young-Suk Lee, Ramon Fernandez Astudillo, Tahira Naseem et al.

Abstract Meaning Representation (AMR) parsing has experienced a notable growth in performance in the last two years, due both to the impact of transfer learning and the development of novel architectures specific to AMR. At the same time, self-learning techniques have helped push the performance boundaries of other natural language processing applications, such as machine translation or question answering. In this paper, we explore different ways in which trained models can be applied to improve AMR parsing performance, including generation of synthetic text and AMR annotations as well as refinement of actions oracle. We show that, without any additional human annotations, these techniques improve an already performant parser and achieve state-of-the-art results on AMR 1.0 and AMR 2.0.

Ramon Fernandez Astudillo, Miguel Ballesteros, Tahira Naseem et al.

Modeling the parser state is key to good performance in transition-based parsing. Recurrent Neural Networks considerably improved the performance of transition-based systems by modelling the global state, e.g. stack-LSTM parsers, or local state modeling of contextualized features, e.g. Bi-LSTM parsers. Given the success of Transformer architectures in recent parsing systems, this work explores modifications of the sequence-to-sequence Transformer architecture to model either global or local parser states in transition-based parsing. We show that modifications of the cross attention mechanism of the Transformer considerably strengthen performance both on dependency and Abstract Meaning Representation (AMR) parsing tasks, particularly for smaller models or limited training data.

Jian Ni, Taesun Moon, Parul Awasthy et al.

Relation extraction (RE) is one of the most important tasks in information extraction, as it provides essential information for many NLP applications. In this paper, we propose a cross-lingual RE approach that does not require any human annotation in a target language or any cross-lingual resources. Building upon unsupervised cross-lingual representation learning frameworks, we develop several deep Transformer based RE models with a novel encoding scheme that can effectively encode both entity location and entity type information. Our RE models, when trained with English data, outperform several deep neural network based English RE models. More importantly, our models can be applied to perform zero-shot cross-lingual RE, achieving the state-of-the-art cross-lingual RE performance on two datasets (68-89% of the accuracy of the supervised target-language RE model). The high cross-lingual transfer efficiency without requiring additional training data or cross-lingual resources shows that our RE models are especially useful for low-resource languages.

Rong Zhang, Revanth Gangi Reddy, Md Arafat Sultan et al.

Transfer learning techniques are particularly useful in NLP tasks where a sizable amount of high-quality annotated data is difficult to obtain. Current approaches directly adapt a pre-trained language model (LM) on in-domain text before fine-tuning to downstream tasks. We show that extending the vocabulary of the LM with domain-specific terms leads to further gains. To a bigger effect, we utilize structure in the unlabeled data to create auxiliary synthetic tasks, which helps the LM transfer to downstream tasks. We apply these approaches incrementally on a pre-trained Roberta-large LM and show considerable performance gain on three tasks in the IT domain: Extractive Reading Comprehension, Document Ranking and Duplicate Question Detection.

Parul Awasthy, Taesun Moon, Jian Ni et al.

Named Entity Recognition (NER) is an essential precursor task for many natural language applications, such as relation extraction or event extraction. Much of the NER research has been done on datasets with few classes of entity types (e.g. PER, LOC, ORG, MISC), but many real world applications (disaster relief, complex event extraction, law enforcement) can benefit from a larger NER typeset. More recently, datasets were created that have hundreds to thousands of types of entities, sparking new lines of research (Sekine, 2008;Ling and Weld, 2012; Gillick et al., 2014; Choiet al., 2018). In this paper we present a cascaded approach to labeling fine-grained NER, applying to a newly released fine-grained NER dataset that was used in the TAC KBP 2019 evaluation (Ji et al., 2019), inspired by the fact that training data is available for some of the coarse labels. Using a combination of transformer networks, we show that performance can be improved by about 20 F1 absolute, as compared with the straightforward model built on the full fine-grained types, and show that, surprisingly, using course-labeled data in three languages leads to an improvement in the English data.

Parul Awasthy, Tahira Naseem, Jian Ni et al.

The task of event detection and classification is central to most information retrieval applications. We show that a Transformer based architecture can effectively model event extraction as a sequence labeling task. We propose a combination of sentence level and token level training objectives that significantly boosts the performance of a BERT based event extraction model. Our approach achieves a new state-of-the-art performance on ACE 2005 data for English and Chinese. We also test our model on ERE Spanish, achieving an average gain of 2 absolute F1 points over prior best performing model.

Manuel Mager, Ramon Fernandez Astudillo, Tahira Naseem et al.

Meaning Representations (AMRs) are broad-coverage sentence-level semantic graphs. Existing approaches to generating text from AMR have focused on training sequence-to-sequence or graph-to-sequence models on AMR annotated data only. In this paper, we propose an alternative approach that combines a strong pre-trained language model with cycle consistency-based re-scoring. Despite the simplicity of the approach, our experimental results show these models outperform all previous techniques on the English LDC2017T10dataset, including the recent use of transformer architectures. In addition to the standard evaluation metrics, we provide human evaluation experiments that further substantiate the strength of our approach.

Taesun Moon, Parul Awasthy, Jian Ni et al.

Information extraction is an important task in NLP, enabling the automatic extraction of data for relational database filling. Historically, research and data was produced for English text, followed in subsequent years by datasets in Arabic, Chinese (ACE/OntoNotes), Dutch, Spanish, German (CoNLL evaluations), and many others. The natural tendency has been to treat each language as a different dataset and build optimized models for each. In this paper we investigate a single Named Entity Recognition model, based on a multilingual BERT, that is trained jointly on many languages simultaneously, and is able to decode these languages with better accuracy than models trained only on one language. To improve the initial model, we study the use of regularization strategies such as multitask learning and partial gradient updates. In addition to being a single model that can tackle multiple languages (including code switch), the model could be used to make zero-shot predictions on a new language, even ones for which training data is not available, out of the box. The results show that this model not only performs competitively with monolingual models, but it also achieves state-of-the-art results on the CoNLL02 Dutch and Spanish datasets, OntoNotes Arabic and Chinese datasets. Moreover, it performs reasonably well on unseen languages, achieving state-of-the-art for zero-shot on three CoNLL languages.

Vittorio Castelli, Rishav Chakravarti, Saswati Dana et al.

We introduce TechQA, a domain-adaptation question answering dataset for the technical support domain. The TechQA corpus highlights two real-world issues from the automated customer support domain. First, it contains actual questions posed by users on a technical forum, rather than questions generated specifically for a competition or a task. Second, it has a real-world size -- 600 training, 310 dev, and 490 evaluation question/answer pairs -- thus reflecting the cost of creating large labeled datasets with actual data. Consequently, TechQA is meant to stimulate research in domain adaptation rather than being a resource to build QA systems from scratch. The dataset was obtained by crawling the IBM Developer and IBM DeveloperWorks forums for questions with accepted answers that appear in a published IBM Technote---a technical document that addresses a specific technical issue. We also release a collection of the 801,998 publicly available Technotes as of April 4, 2019 as a companion resource that might be used for pretraining, to learn representations of the IT domain language.

Jian Ni, Radu Florian

Relation extraction (RE) seeks to detect and classify semantic relationships between entities, which provides useful information for many NLP applications. Since the state-of-the-art RE models require large amounts of manually annotated data and language-specific resources to achieve high accuracy, it is very challenging to transfer an RE model of a resource-rich language to a resource-poor language. In this paper, we propose a new approach for cross-lingual RE model transfer based on bilingual word embedding mapping. It projects word embeddings from a target language to a source language, so that a well-trained source-language neural network RE model can be directly applied to the target language. Experiment results show that the proposed approach achieves very good performance for a number of target languages on both in-house and open datasets, using a small bilingual dictionary with only 1K word pairs.

Anthony Ferritto, Lin Pan, Rishav Chakravarti et al.

Many of the top question answering systems today utilize ensembling to improve their performance on tasks such as the Stanford Question Answering Dataset (SQuAD) and Natural Questions (NQ) challenges. Unfortunately most of these systems do not publish their ensembling strategies used in their leaderboard submissions. In this work, we investigate a number of ensembling techniques and demonstrate a strategy which improves our F1 score for short answers on the dev set for NQ by 2.3 F1 points over our single model (which outperforms the previous SOTA by 1.9 F1 points).

Lin Pan, Rishav Chakravarti, Anthony Ferritto et al.

Existing literature on Question Answering (QA) mostly focuses on algorithmic novelty, data augmentation, or increasingly large pre-trained language models like XLNet and RoBERTa. Additionally, a lot of systems on the QA leaderboards do not have associated research documentation in order to successfully replicate their experiments. In this paper, we outline these algorithmic components such as Attention-over-Attention, coupled with data augmentation and ensembling strategies that have shown to yield state-of-the-art results on benchmark datasets like SQuAD, even achieving super-human performance. Contrary to these prior results, when we evaluate on the recently proposed Natural Questions benchmark dataset, we find that an incredibly simple approach of transfer learning from BERT outperforms the previous state-of-the-art system trained on 4 million more examples than ours by 1.9 F1 points. Adding ensembling strategies further improves that number by 2.3 F1 points.

Rishav Chakravarti, Cezar Pendus, Andrzej Sakrajda et al.

This paper introduces a novel orchestration framework, called CFO (COMPUTATION FLOW ORCHESTRATOR), for building, experimenting with, and deploying interactive NLP (Natural Language Processing) and IR (Information Retrieval) systems to production environments. We then demonstrate a question answering system built using this framework which incorporates state-of-the-art BERT based MRC (Machine Reading Comprehension) with IR components to enable end-to-end answer retrieval. Results from the demo system are shown to be high quality in both academic and industry domain specific settings. Finally, we discuss best practices when (pre-)training BERT based MRC models for production systems.

Tahira Naseem, Abhishek Shah, Hui Wan et al.

Our work involves enriching the Stack-LSTM transition-based AMR parser (Ballesteros and Al-Onaizan, 2017) by augmenting training with Policy Learning and rewarding the Smatch score of sampled graphs. In addition, we also combined several AMR-to-text alignments with an attention mechanism and we supplemented the parser with pre-processed concept identification, named entities and contextualized embeddings. We achieve a highly competitive performance that is comparable to the best published results. We show an in-depth study ablating each of the new components of the parser

Linfeng Song, Zhiguo Wang, Mo Yu et al.

Multi-hop reading comprehension focuses on one type of factoid question, where a system needs to properly integrate multiple pieces of evidence to correctly answer a question. Previous work approximates global evidence with local coreference information, encoding coreference chains with DAG-styled GRU layers within a gated-attention reader. However, coreference is limited in providing information for rich inference. We introduce a new method for better connecting global evidence, which forms more complex graphs compared to DAGs. To perform evidence integration on our graphs, we investigate two recent graph neural networks, namely graph convolutional network (GCN) and graph recurrent network (GRN). Experiments on two standard datasets show that richer global information leads to better answers. Our method performs better than all published results on these datasets.

Gourab Kundu, Avirup Sil, Radu Florian et al.

We propose an entity-centric neural cross-lingual coreference model that builds on multi-lingual embeddings and language-independent features. We perform both intrinsic and extrinsic evaluations of our model. In the intrinsic evaluation, we show that our model, when trained on English and tested on Chinese and Spanish, achieves competitive results to the models trained directly on Chinese and Spanish respectively. In the extrinsic evaluation, we show that our English model helps achieve superior entity linking accuracy on Chinese and Spanish test sets than the top 2015 TAC system without using any annotated data from Chinese or Spanish.

Avirup Sil, Gourab Kundu, Radu Florian et al.

A major challenge in Entity Linking (EL) is making effective use of contextual information to disambiguate mentions to Wikipedia that might refer to different entities in different contexts. The problem exacerbates with cross-lingual EL which involves linking mentions written in non-English documents to entries in the English Wikipedia: to compare textual clues across languages we need to compute similarity between textual fragments across languages. In this paper, we propose a neural EL model that trains fine-grained similarities and dissimilarities between the query and candidate document from multiple perspectives, combined with convolution and tensor networks. Further, we show that this English-trained system can be applied, in zero-shot learning, to other languages by making surprisingly effective use of multi-lingual embeddings. The proposed system has strong empirical evidence yielding state-of-the-art results in English as well as cross-lingual: Spanish and Chinese TAC 2015 datasets.