BERT for Coreference Resolution: Baselines and Analysis
Not on the map. Why?
Abstract (arXiv)
We apply BERT to coreference resolution, achieving strong improvements on the OntoNotes (+3.9 F1) and GAP (+11.5 F1) benchmarks. A qualitative analysis of model predictions indicates that, compared to ELMo and BERT-base, BERT-large is particularly better at distinguishing between related but distinct entities (e.g., President and CEO). However, there is still room for improvement in modeling document-level context, conversations, and mention paraphrasing. Our code and models are publicly available.
Key facts. Cited by 125 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Aug 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 36; 2022: 31; 2023: 25; 2024: 17; 2025: 9; 2026: 7.
125 papers.
Sort:
By area:
- 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 663
- 2021Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Surveycited by 457
- 2021Structured Prediction as Translation between Augmented Natural Languagescited by 183
- 2022MAVEN-ERE: A Unified Large-scale Dataset for Event Coreference, Temporal, Causal, and Subevent Relation Extractioncited by 65
- 2021Collecting a Large-Scale Gender Bias Dataset for Coreference Resolution and Machine Translationcited by 62
- 2021"Let Your Characters Tell Their Story": A Dataset for Character-Centric Narrative Understandingcited by 48
- 2021Coreference Resolution without Span Representationscited by 45
- 2022DeepStruct: Pretraining of Language Models for Structure Predictioncited by 45
- 2022Autoregressive Structured Prediction with Language Modelscited by 43
- 2022Grad-SAM: Explaining Transformers via Gradient Self-Attention Mapscited by 42
- 2022Coreference Resolution through a seq2seq Transition-Based Systemcited by 34
- 2021Cross-document Coreference Resolution over Predicted Mentionscited by 29
38 more
- 2022Attention Mechanism in Neural Networks: Where it Comes and Where it Goescited by 29
- 2022LingMess: Linguistically Informed Multi Expert Scorers for Coreference Resolutioncited by 26
- 2023FACTIFY-5WQA: 5W Aspect-based Fact Verification through Question Answeringcited by 24
- 2021LOME: Large Ontology Multilingual Extractioncited by 23
- 2021WEC: Deriving a Large-scale Cross-document Event Coreference dataset from Wikipediacited by 23
- 2022F-coref: Fast, Accurate and Easy to Use Coreference Resolutioncited by 23
- 2022The NLP Task Effectiveness of Long-Range Transformerscited by 22
- 2021CIDER: Commonsense Inference for Dialogue Explanation and Reasoningcited by 20
- 2022Naturalistic Causal Probing for Morpho-Syntaxcited by 19
- 2024Maverick: Efficient and Accurate Coreference Resolution Defying Recent Trendscited by 19
- 2021Moving on from OntoNotes: Coreference Resolution Model Transfercited by 18
- 2021OntoGUM: Evaluating Contextualized SOTA Coreference Resolution on 12 More Genrescited by 18
- 2023BERT Based Clinical Knowledge Extraction for Biomedical Knowledge Graph Construction and Analysiscited by 18
- 2021CDLM: Cross-Document Language Modelingcited by 17
- 2023Med-EASi: Finely Annotated Dataset and Models for Controllable Simplification of Medical Textscited by 16
- 2021Realistic Evaluation Principles for Cross-document Coreference Resolutioncited by 15
- 2023FACTIFY3M: A Benchmark for Multimodal Fact Verification with Explainability through 5W Question-Answeringcited by 15
- 2024OpenPSG: Open-set Panoptic Scene Graph Generation via Large Multimodal Modelscited by 15
- 2023TempEL: Linking Dynamically Evolving and Newly Emerging Entitiescited by 14
- 2021CREAD: Combined Resolution of Ellipses and Anaphora in Dialoguescited by 13
- 2021Multilingual Coreference Resolution with Harmonized Annotationscited by 13
- 2021Sequential Cross-Document Coreference Resolutioncited by 12
- 2022Cross-document Event Coreference Search: Task, Dataset and Modelingcited by 12
- 2023AmbiCoref: Evaluating Human and Model Sensitivity to Ambiguous Coreferencecited by 12
- 2022Entity-aware Transformers for Entity Searchcited by 10
- 2023Seq2seq is All You Need for Coreference Resolutioncited by 10
- 2024Leveraging Long-Context Large Language Models for Multi-Document Understanding and Summarization in Enterprise Applicationscited by 10
- 2021Conversational Semantic Role Labelingcited by 8
- 2022Towards WinoQueer: Developing a Benchmark for Anti-Queer Bias in Large Language Modelscited by 8
- 2022'UFAL CorPipe at CRAC 2022: Effectivity of Multilingual Models for Coreference Resolutioncited by 8
- 2024[Lions: 1] and [Tigers: 2] and [Bears: 3], Oh My! Literary Coreference Annotation with LLMscited by 8
- 2024Evaluating LLMs for Quotation Attribution in Literary Texts: A Case Study of LLaMa3cited by 8
- 2021End-to-end Neural Coreference Resolution Revisited: A Simple yet Effective Baselinecited by 7
- 2022Graph Refinement for Coreference Resolutioncited by 7
- 2022VD-PCR: Improving Visual Dialog with Pronoun Coreference Resolutioncited by 7
- 2023Introducing Rhetorical Parallelism Detection: A New Task with Datasets, Metrics, and Baselinescited by 7
- 2021Joint Coreference Resolution and Character Linking for Multiparty Conversationcited by 6
- 2021Towards Consistent Document-level Entity Linking: Joint Models for Entity Linking and Coreference Resolutioncited by 6
50 most cited of 125 All 125 (JSON)
- 2026Contrastive Learning for Authorship Verification23 Sep 2026
- 2026LLMs+Graphs: Toward Graph-Native, Synergistic AI Systems10 Jun 2026
- 2026Multilingual Coreference Resolution via Cycle-Consistent Machine Translation3 Jun 2026
- 2026CorPipe at CRAC 2026: Empty Nodes and Cross-Lingual Transfer in Multilingual Coreference Resolution28 May 2026
- 2026Closing the Gap at CRAC 2026: Two-Stage Adaptation for LLM-Based Multilingual Coreference Resolution16 May 2026
- 2026ReCap: Lightweight Referential Grounding for Coherent Story Visualization20 Apr 2026
- 2026Beyond Word Boundaries: A Hebrew Coreference Benchmark and an Evaluation Protocol for Morphologically Complex Text18 Apr 2026
- 2025Moneyball with LLMs: Analyzing Tabular Summarization in Sports Narratives20 Oct 2025
- 2025The Elephant in the Coreference Room: Resolving Coreference in Full-Length French Fiction Works17 Oct 2025
- 2025An Senegalese Legal Texts Structuration Using LLM-augmented Knowledge Graph27 Sep 2025
- 2025Mah=an=ama: A Unique Testbed for Literary Entity Discovery and Linking24 Sep 2025
- 2025CorPipe at CRAC 2025: Evaluating Multilingual Encoders for Multilingual Coreference Resolution22 Sep 2025
38 more
- 2025Improving LLMs' Learning for Coreference Resolution14 Sep 2025
- 2025RAKG:Document-level Retrieval Augmented Knowledge Graph Construction14 Apr 2025
- 2025ARLED: Leveraging LED-based ARMAN Model for Abstractive Summarization of Persian Long Documents13 Mar 2025
- 2025Evaluating Discourse Cohesion in Pre-trained Language Models8 Mar 2025
- 2024Graph Neural Networks on Discriminative Graphs of Words27 Oct 2024
- 2024CorPipe at CRAC 2024: Predicting Zero Mentions from Raw Text3 Oct 2024
- 2024Leveraging Long-Context Large Language Models for Multi-Document Understanding and Summarization in Enterprise Applications27 Sep 2024
- 2024Exploring Multiple Strategies to Improve Multilingual Coreference Resolution in CorefUD29 Aug 2024
- 2024Maverick: Efficient and Accurate Coreference Resolution Defying Recent Trends31 Jul 2024
- 2024OpenPSG: Open-set Panoptic Scene Graph Generation via Large Multimodal Models15 Jul 2024
- 2024EasyECR: A Library for Easy Implementation and Evaluation of Event Coreference Resolution Models20 Jun 2024
- 2024Evaluating LLMs for Quotation Attribution in Literary Texts: A Case Study of LLaMa317 Jun 2024
- 2024ThaiCoref: Thai Coreference Resolution Dataset10 Jun 2024
- 2024Persian Pronoun Resolution: Leveraging Neural Networks and Language Models17 May 2024
- 2024Mesh Denoising Transformer10 May 2024
- 2024KoCoNovel: Annotated Dataset of Character Coreference in Korean Novels1 Apr 2024
- 2024A Controlled Reevaluation of Coreference Resolution Models31 Mar 2024
- 2024Computational Modelling of Plurality and Definiteness in Chinese Noun Phrases7 Mar 2024
- 2024Multilingual Coreference Resolution in Low-resource South Asian Languages21 Feb 2024
- 2024[Lions: 1] and [Tigers: 2] and [Bears: 3], Oh My! Literary Coreference Annotation with LLMs31 Jan 2024
- 2024Fine-tuning Transformer-based Encoder for Turkish Language Understanding Tasks30 Jan 2024
- 2023Introducing Rhetorical Parallelism Detection: A New Task with Datasets, Metrics, and Baselines30 Nov 2023
- 2023Transformers as Graph-to-Graph Models27 Oct 2023
- 2023Investigating Multilingual Coreference Resolution by Universal Annotations26 Oct 2023
- 2023Seq2seq is All You Need for Coreference Resolution20 Oct 2023
- 2023ProtoEM: A Prototype-Enhanced Matching Framework for Event Relation Extraction22 Sep 2023
- 2023RGAT: A Deeper Look into Syntactic Dependency Information for Coreference Resolution10 Sep 2023
- 2023MultiSChuBERT: Effective Multimodal Fusion for Scholarly Document Quality Prediction15 Aug 2023
- 2023DialogRE^C+: An Extension of DialogRE to Investigate How Much Coreference Helps Relation Extraction in Dialogs8 Aug 2023
- 2023Unifying Large Language Models and Knowledge Graphs: A Roadmap14 Jun 2023
- 2023Parallel Data Helps Neural Entity Coreference Resolution28 May 2023
- 2023Sentence-Incremental Neural Coreference Resolution26 May 2023
- 2023Arukikata Travelogue Dataset with Geographic Entity Mention, Coreference, and Link Annotation23 May 2023
- 2023FACTIFY3M: A Benchmark for Multimodal Fact Verification with Explainability through 5W Question-Answering22 May 2023
- 2023FACTIFY-5WQA: 5W Aspect-based Fact Verification through Question Answering7 May 2023
- 2023BERT Based Clinical Knowledge Extraction for Biomedical Knowledge Graph Construction and Analysis21 Apr 2023
- 2023Multidimensional Perceptron for Efficient and Explainable Long Text Classification4 Apr 2023
- 2023Spelling convention sensitivity in neural language models6 Mar 2023
50 newest of 125 All 125 (JSON)
- 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 663
- 2021Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Surveycited by 457
- 2021Structured Prediction as Translation between Augmented Natural Languagescited by 183
- 2022MAVEN-ERE: A Unified Large-scale Dataset for Event Coreference, Temporal, Causal, and Subevent Relation Extractioncited by 65
- 2021Collecting a Large-Scale Gender Bias Dataset for Coreference Resolution and Machine Translationcited by 62
- 2021"Let Your Characters Tell Their Story": A Dataset for Character-Centric Narrative Understandingcited by 48
- 2021Coreference Resolution without Span Representationscited by 45
- 2022DeepStruct: Pretraining of Language Models for Structure Predictioncited by 45
- 2022Autoregressive Structured Prediction with Language Modelscited by 43
- 2022Grad-SAM: Explaining Transformers via Gradient Self-Attention Mapscited by 42
- 2022Coreference Resolution through a seq2seq Transition-Based Systemcited by 34
- 2021Cross-document Coreference Resolution over Predicted Mentionscited by 29
12 most cited of 122 All 122 (JSON)
- 2026Contrastive Learning for Authorship Verification23 Sep 2026
- 2026Multilingual Coreference Resolution via Cycle-Consistent Machine Translation3 Jun 2026
- 2026CorPipe at CRAC 2026: Empty Nodes and Cross-Lingual Transfer in Multilingual Coreference Resolution28 May 2026
- 2026Closing the Gap at CRAC 2026: Two-Stage Adaptation for LLM-Based Multilingual Coreference Resolution16 May 2026
- 2026ReCap: Lightweight Referential Grounding for Coherent Story Visualization20 Apr 2026
- 2026Beyond Word Boundaries: A Hebrew Coreference Benchmark and an Evaluation Protocol for Morphologically Complex Text18 Apr 2026
- 2025Moneyball with LLMs: Analyzing Tabular Summarization in Sports Narratives20 Oct 2025
- 2025The Elephant in the Coreference Room: Resolving Coreference in Full-Length French Fiction Works17 Oct 2025
- 2025An Senegalese Legal Texts Structuration Using LLM-augmented Knowledge Graph27 Sep 2025
- 2025Mah=an=ama: A Unique Testbed for Literary Entity Discovery and Linking24 Sep 2025
- 2025CorPipe at CRAC 2025: Evaluating Multilingual Encoders for Multilingual Coreference Resolution22 Sep 2025
- 2025Improving LLMs' Learning for Coreference Resolution14 Sep 2025
12 newest of 122 All 122 (JSON)