Multimodal reference resolution, including phrase grounding, aims to understand the semantic relations between mentions and real-world objects. Phrase grounding between images and their captions is a well-established task. In contrast, for real-world applications, it is essential to integrate textual and multimodal reference resolution to unravel the reference relations within dialogue, especially in handling ambiguities caused by pronouns and ellipses. This paper presents a framework that unifies textual and multimodal reference resolution by mapping mention embeddings to object embeddings and selecting mentions or objects based on their similarity. Our experiments show that learning textual reference resolution, such as coreference resolution and predicate-argument structure analysis, positively affects performance in multimodal reference resolution. In particular, our model with coreference resolution performs better in pronoun phrase grounding than representative models for this task, MDETR and GLIP. Our qualitative analysis demonstrates that incorporating textual reference relations strengthens the confidence scores between mentions, including pronouns and predicates, and objects, which can reduce the ambiguities that arise in visually grounded dialogues.
With the rise of knowledge graph based retrieval-augmented generation (RAG) techniques such as GraphRAG and Pike-RAG, the role of knowledge graphs in enhancing the reasoning capabilities of large language models (LLMs) has become increasingly prominent. However, traditional Knowledge Graph Construction (KGC) methods face challenges like complex entity disambiguation, rigid schema definition, and insufficient cross-document knowledge integration. This paper focuses on the task of automatic document-level knowledge graph construction. It proposes the Document-level Retrieval Augmented Knowledge Graph Construction (RAKG) framework. RAKG extracts pre-entities from text chunks and utilizes these pre-entities as queries for RAG, effectively addressing the issue of long-context forgetting in LLMs and reducing the complexity of Coreference Resolution. In contrast to conventional KGC methods, RAKG more effectively captures global information and the interconnections among disparate nodes, thereby enhancing the overall performance of the model. Additionally, we transfer the RAG evaluation framework to the KGC field and filter and evaluate the generated knowledge graphs, thereby avoiding incorrectly generated entities and relationships caused by hallucinations in LLMs. We further developed the MINE dataset by constructing standard knowledge graphs for each article and experimentally validated the performance of RAKG. The results show that RAKG achieves an accuracy of 95.91 % on the MINE dataset, a 6.2 % point improvement over the current best baseline, GraphRAG (89.71 %). The code is available at https://github.com/LMMApplication/RAKG.
Question Answering (QA) tasks, which involve extracting answers from a given context, are relatively straightforward for modern Large Language Models (LLMs) when the context is short. However, long contexts pose challenges due to the quadratic complexity of the self-attention mechanism. This challenge is compounded in Indic languages, which are often low-resource. This study explores context-shortening techniques, including Open Information Extraction (OIE), coreference resolution, Answer Paragraph Selection (APS), and their combinations, to improve QA performance. Compared to the baseline of unshortened (long) contexts, our experiments on four Indic languages (Hindi, Tamil, Telugu, and Urdu) demonstrate that context-shortening techniques yield an average improvement of 4\% in semantic scores and 47\% in token-level scores when evaluated on three popular LLMs without fine-tuning. Furthermore, with fine-tuning, we achieve an average increase of 2\% in both semantic and token-level scores. Additionally, context-shortening reduces computational overhead. Explainability techniques like LIME and SHAP reveal that when the APS model confidently identifies the paragraph containing the answer, nearly all tokens within the selected text receive high relevance scores. However, the study also highlights the limitations of LLM-based QA systems in addressing non-factoid questions, particularly those requiring reasoning or debate. Moreover, verbalizing OIE-generated triples does not enhance system performance. These findings emphasize the potential of context-shortening techniques to improve the efficiency and effectiveness of LLM-based QA systems, especially for low-resource languages. The source code and resources are available at https://github.com/ritwikmishra/IndicGenQA.
Recognizing events and their coreferential mentions in a document is essential for understanding semantic meanings of text. The existing research on event coreference resolution is mostly limited to news articles. In this paper, we present the first dataset for the legal domain, LegalCore, which has been annotated with comprehensive event and event coreference information. The legal contract documents we annotated in this dataset are several times longer than news articles, with an average length of around 25k tokens per document. The annotations show that legal documents have dense event mentions and feature both short-distance and super long-distance coreference links between event mentions. We further benchmark mainstream Large Language Models (LLMs) on this dataset for both event detection and event coreference resolution tasks, and find that this dataset poses significant challenges for state-of-the-art open-source and proprietary LLMs, which perform significantly worse than a supervised baseline. We will publish the dataset as well as the code.
The automatic extraction of character networks from literary texts is generally carried out using natural language processing (NLP) cascading pipelines. While this approach is widespread, no study exists on the impact of low-level NLP tasks on their performance. In this article, we conduct such a study on a literary dataset, focusing on the role of named entity recognition (NER) and coreference resolution when extracting co-occurrence networks. To highlight the impact of these tasks' performance, we start with gold-standard annotations, progressively add uniformly distributed errors, and observe their impact in terms of character network quality. We demonstrate that NER performance depends on the tested novel and strongly affects character detection. We also show that NER-detected mentions alone miss a lot of character co-occurrences, and that coreference resolution is needed to prevent this. Finally, we present comparison points with 2 methods based on large language models (LLMs), including a fully end-to-end one, and show that these models are outperformed by traditional NLP pipelines in terms of recall.
Recent evaluations of LLMs on coreference resolution have revealed that traditional output formats and evaluation metrics do not fully capture the models' referential understanding. To address this, we introduce IdentifyMe, a new benchmark for mention resolution presented in a multiple-choice question (MCQ) format, commonly used for evaluating LLMs. IdentifyMe features long narratives and employs heuristics to exclude easily identifiable mentions, creating a more challenging task. The benchmark also consists of a curated mixture of different mention types and corresponding entities, allowing for a fine-grained analysis of model performance. We evaluate both closed- and open source LLMs on IdentifyMe and observe a significant performance gap (20-30%) between the state-of-the-art sub-10B open models vs. closed ones. We observe that pronominal mentions, which have limited surface information, are typically much harder for models to resolve than nominal mentions. Additionally, we find that LLMs often confuse entities when their mentions overlap in nested structures. The highest-scoring model, GPT-4o, achieves 81.9% accuracy, highlighting the strong referential capabilities of state-of-the-art LLMs while also indicating room for further improvement.
While coreference resolution is traditionally used as a component in individual document understanding, in this work we take a more global view and explore what can we learn about a domain from the set of all document-level coreference relations that are present in a large corpus. We derive coreference chains from a corpus of 30 million biomedical abstracts and construct a graph based on the string phrases within these chains, establishing connections between phrases if they co-occur within the same coreference chain. We then use the graph structure and the betweeness centrality measure to distinguish between edges denoting hierarchy, identity and noise, assign directionality to edges denoting hierarchy, and split nodes (strings) that correspond to multiple distinct concepts. The result is a rich, data-driven ontology over concepts in the biomedical domain, parts of which overlaps significantly with human-authored ontologies. We release the coreference chains and resulting ontology under a creative-commons license, along with the code.
The paper presents an overview of the third edition of the shared task on multilingual coreference resolution, held as part of the CRAC 2024 workshop. Similarly to the previous two editions, the participants were challenged to develop systems capable of identifying mentions and clustering them based on identity coreference. This year's edition took another step towards real-world application by not providing participants with gold slots for zero anaphora, increasing the task's complexity and realism. In addition, the shared task was expanded to include a more diverse set of languages, with a particular focus on historical languages. The training and evaluation data were drawn from version 1.2 of the multilingual collection of harmonized coreference resources CorefUD, encompassing 21 datasets across 15 languages. 6 systems competed in this shared task.
Challenge sets such as the Winograd Schema Challenge (WSC) are used to benchmark systems' ability to resolve ambiguities in natural language. If one assumes as in existing work that solving a given challenge set is at least as difficult as solving some more general task, then high performance on the challenge set should indicate high performance on the general task overall. However, we show empirically that this assumption of difficulty does not always hold. In particular, we demonstrate that despite the strong performance of prompted language models (LMs) on the WSC and its variants, these same modeling techniques perform relatively poorly at resolving certain pronominal ambiguities attested in OntoNotes and related datasets that are perceived to be easier. Motivated by these findings, we propose a method for ensembling a prompted LM with a supervised, task-specific system that is overall more accurate at resolving pronominal coreference across datasets. Finally, we emphasize that datasets involving the same linguistic phenomenon draw on distinct, but overlapping, capabilities, and evaluating on any one dataset alone does not provide a complete picture of a system's overall capability.
Transformer-based language models have shown an excellent ability to effectively capture and utilize contextual information. Although various analysis techniques have been used to quantify and trace the contribution of single contextual cues to a target task such as subject-verb agreement or coreference resolution, scenarios in which multiple relevant cues are available in the context remain underexplored. In this paper, we investigate how language models handle gender agreement when multiple gender cue words are present, each capable of independently disambiguating a target gender pronoun. We analyze two widely used Transformer-based models: BERT, an encoder-based, and GPT-2, a decoder-based model. Our analysis employs two complementary approaches: context mixing analysis, which tracks information flow within the model, and a variant of activation patching, which measures the impact of cues on the model's prediction. We find that BERT tends to prioritize the first cue in the context to form both the target word representations and the model's prediction, while GPT-2 relies more on the final cue. Our findings reveal striking differences in how encoder-based and decoder-based models prioritize and use contextual information for their predictions.
We present CorPipe 24, the winning entry to the CRAC 2024 Shared Task on Multilingual Coreference Resolution. In this third iteration of the shared task, a novel objective is to also predict empty nodes needed for zero coreference mentions (while the empty nodes were given on input in previous years). This way, coreference resolution can be performed on raw text. We evaluate two model variants: a~two-stage approach (where the empty nodes are predicted first using a pretrained encoder model and then processed together with sentence words by another pretrained model) and a single-stage approach (where a single pretrained encoder model generates empty nodes, coreference mentions, and coreference links jointly). In both settings, CorPipe surpasses other participants by a large margin of 3.9 and 2.8 percent points, respectively. The source code and the trained model are available at https://github.com/ufal/crac2024-corpipe.
This paper explores the challenges posed by nominal adjectives (NAs) in natural language processing (NLP) tasks, particularly in part-of-speech (POS) tagging. We propose treating NAs as a distinct POS tag, "JN," and investigate its impact on POS tagging, BIO chunking, and coreference resolution. Our study shows that reclassifying NAs can improve the accuracy of syntactic analysis and structural understanding in NLP. We present experimental results using Hidden Markov Models (HMMs), Maximum Entropy (MaxEnt) models, and Spacy, demonstrating the feasibility and potential benefits of this approach. Additionally we finetuned a bert model to identify the NA in untagged text.
While measuring bias and robustness in coreference resolution are important goals, such measurements are only as good as the tools we use to measure them. Winogender Schemas (Rudinger et al., 2018) are an influential dataset proposed to evaluate gender bias in coreference resolution, but a closer look reveals issues with the data that compromise its use for reliable evaluation, including treating different pronominal forms as equivalent, violations of template constraints, and typographical errors. We identify these issues and fix them, contributing a new dataset: WinoPron. Using WinoPron, we evaluate two state-of-the-art supervised coreference resolution systems, SpanBERT, and five sizes of FLAN-T5, and demonstrate that accusative pronouns are harder to resolve for all models. We also propose a new method to evaluate pronominal bias in coreference resolution that goes beyond the binary. With this method, we also show that bias characteristics vary not just across pronoun sets (e.g., he vs. she), but also across surface forms of those sets (e.g., him vs. his).
Coreference resolution, the task of identifying expressions in text that refer to the same entity, is a critical component in various natural language processing applications. This paper presents a novel end-to-end neural coreference resolution system utilizing the CorefUD 1.1 dataset, which spans 17 datasets across 12 languages. The proposed model is based on the standard end-to-end neural coreference resolution system. We first establish baseline models, including monolingual and cross-lingual variations, and then propose several extensions to enhance performance across diverse linguistic contexts. These extensions include cross-lingual training, incorporation of syntactic information, a Span2Head model for optimized headword prediction, and advanced singleton modeling. We also experiment with headword span representation and long-documents modeling through overlapping segments. The proposed extensions, particularly the heads-only approach, singleton modeling, and long document prediction, significantly improve performance across most datasets. We also perform zero-shot cross-lingual experiments, highlighting the potential and limitations of cross-lingual transfer in coreference resolution. Our findings contribute to the development of robust and scalable coreference systems for multilingual coreference resolution. Finally, we evaluate our model on the CorefUD 1.1 test set and surpass the best model from the CRAC 2023 shared task of comparable size by a large margin.
Large autoregressive generative models have emerged as the cornerstone for achieving the highest performance across several Natural Language Processing tasks. However, the urge to attain superior results has, at times, led to the premature replacement of carefully designed task-specific approaches without exhaustive experimentation. The Coreference Resolution task is no exception; all recent state-of-the-art solutions adopt large generative autoregressive models that outperform encoder-based discriminative systems. In this work,we challenge this recent trend by introducing Maverick, a carefully designed - yet simple - pipeline, which enables running a state-of-the-art Coreference Resolution system within the constraints of an academic budget, outperforming models with up to 13 billion parameters with as few as 500 million parameters. Maverick achieves state-of-the-art performance on the CoNLL-2012 benchmark, training with up to 0.006x the memory resources and obtaining a 170x faster inference compared to previous state-of-the-art systems. We extensively validate the robustness of the Maverick framework with an array of diverse experiments, reporting improvements over prior systems in data-scarce, long-document, and out-of-domain settings. We release our code and models for research purposes at https://github.com/SapienzaNLP/maverick-coref.
Speech Integrated Large Language Models (SILLMs) combine large language models with speech perception to perform diverse tasks, such as emotion recognition to speaker verification, demonstrating universal audio understanding capability. However, these models may amplify biases present in training data, potentially leading to biased access to information for marginalized groups. This work introduces a curated spoken bias evaluation toolkit and corresponding dataset. We evaluate gender bias in SILLMs across four semantic-related tasks: speech-to-text translation (STT), spoken coreference resolution (SCR), spoken sentence continuation (SSC), and spoken question answering (SQA). Our analysis reveals that bias levels are language-dependent and vary with different evaluation methods. Our findings emphasize the necessity of employing multiple approaches to comprehensively assess biases in SILLMs, providing insights for developing fairer SILLM systems.
Existing cross-document event coreference resolution models, which either compute mention similarity directly or enhance mention representation by extracting event arguments (such as location, time, agent, and patient), lacking the ability to utilize document-level information. As a result, they struggle to capture long-distance dependencies. This shortcoming leads to their underwhelming performance in determining coreference for the events where their argument information relies on long-distance dependencies. In light of these limitations, we propose the construction of document-level Rhetorical Structure Theory (RST) trees and cross-document Lexical Chains to model the structural and semantic information of documents. Subsequently, cross-document heterogeneous graphs are constructed and GAT is utilized to learn the representations of events. Finally, a pair scorer calculates the similarity between each pair of events and co-referred events can be recognized using standard clustering algorithm. Additionally, as the existing cross-document event coreference datasets are limited to English, we have developed a large-scale Chinese cross-document event coreference dataset to fill this gap, which comprises 53,066 event mentions and 4,476 clusters. After applying our model on the English and Chinese datasets respectively, it outperforms all baselines by large margins.
Document-level event extraction aims to extract structured event information from unstructured text. However, a single document often contains limited event information and the roles of different event arguments may be biased due to the influence of the information source. This paper addresses the limitations of traditional document-level event extraction by proposing the task of cross-document event extraction (CDEE) to integrate event information from multiple documents and provide a comprehensive perspective on events. We construct a novel cross-document event extraction dataset, namely CLES, which contains 20,059 documents and 37,688 mention-level events, where over 70% of them are cross-document. To build a benchmark, we propose a CDEE pipeline that includes 5 steps, namely event extraction, coreference resolution, entity normalization, role normalization and entity-role resolution. Our CDEE pipeline achieves about 72% F1 in end-to-end cross-document event extraction, suggesting the challenge of this task. Our work builds a new line of information extraction research and will attract new research attention.
The limited generalization of coreference resolution (CR) models has been a major bottleneck in the task's broad application. Prior work has identified annotation differences, especially for mention detection, as one of the main reasons for the generalization gap and proposed using additional annotated target domain data. Rather than relying on this additional annotation, we propose an alternative referential task, Major Entity Identification (MEI), where we: (a) assume the target entities to be specified in the input, and (b) limit the task to only the frequent entities. Through extensive experiments, we demonstrate that MEI models generalize well across domains on multiple datasets with supervised models and LLM-based few-shot prompting. Additionally, MEI fits the classification framework, which enables the use of robust and intuitive classification-based metrics. Finally, MEI is also of practical use as it allows a user to search for all mentions of a particular entity or a group of entities of interest.
While coreference resolution is a well-established research area in Natural Language Processing (NLP), research focusing on Thai language remains limited due to the lack of large annotated corpora. In this work, we introduce ThaiCoref, a dataset for Thai coreference resolution. Our dataset comprises 777,271 tokens, 44,082 mentions and 10,429 entities across four text genres: university essays, newspapers, speeches, and Wikipedia. Our annotation scheme is built upon the OntoNotes benchmark with adjustments to address Thai-specific phenomena. Utilizing ThaiCoref, we train models employing a multilingual encoder and cross-lingual transfer techniques, achieving a best F1 score of 67.88\% on the test set. Error analysis reveals challenges posed by Thai's unique linguistic features. To benefit the NLP community, we make the dataset and the model publicly available at http://www.github.com/nlp-chula/thai-coref .