mlsanityData to 7 Oct 2026

Modeling Task Interactions in Document-Level Joint Entity and Relation Extraction

arXiv 2205.01909 ↗First posted 4 May 2022cs.CL cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

We target on the document-level relation extraction in an end-to-end setting, where the model needs to jointly perform mention extraction, coreference resolution (COREF) and relation extraction (RE) at once, and gets evaluated in an entity-centric way. Especially, we address the two-way interaction between COREF and RE that has not been the focus by previous work, and propose to introduce explicit interaction namely Graph Compatibility (GC) that is specifically designed to leverage task characteristics, bridging decisions of two tasks for direct task interference. Our experiments are conducted on DocRED and DWIE; in addition to GC, we implement and compare different multi-task settings commonly adopted in previous work, including pipeline, shared encoders, graph propagation, to examine the effectiveness of different interactions. The result shows that GC achieves the best performance by up to 2.3/5.1 F1 improvement over the baseline.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 18 of its 23 references that are in the map. First posted on arXiv 4 May 2022.

Builds on

18 of 23 references.

References · 18

  1. 2017Graph Attention Networkscited by 8,854
  2. 2019SpanBERT: Improving Pre-training by Representing and Predicting Spanscited by 832
  3. 2018Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Constructioncited by 321
  4. 2019Entity, Relation, and Event Extraction with Contextualized Span Representationscited by 261
  5. 2019DocRED: A Large-Scale Document-Level Relation Extraction Datasetcited by 239
  6. 2018Higher-order Coreference Resolution with Coarse-to-fine Inferencecited by 150
  7. 2019BERT for Coreference Resolution: Baselines and Analysiscited by 125
  8. 2020Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Poolingcited by 115
  9. 2020Reasoning with Latent Structure Refinement for Document-Level Relation Extractioncited by 97
  10. 2019A General Framework for Information Extraction using Dynamic Span Graphscited by 93
  11. 2021Entity Structure Within and Throughout: Modeling Mention Dependencies for Document-Level Relation Extractioncited by 68
  12. 2018A Hierarchical Multi-task Approach for Learning Embeddings from Semantic Taskscited by 54
6 more
  1. 2020Revealing the Myth of Higher-Order Inference in Coreference Resolutioncited by 49
  2. 2021An End-to-end Model for Entity-level Relation Extraction using Multi-instance Learningcited by 31
  3. 2020DWIE: an entity-centric dataset for multi-task document-level information extractioncited by 29
  4. 2021Learning Logic Rules for Document-level Relation Extractioncited by 15
  5. 2021Injecting Knowledge Base Information into End-to-End Joint Entity and Relation Extraction and Coreference Resolutioncited by 12
  6. 2021Adapted End-to-End Coreference Resolution System for Anaphoric Identities in Dialoguescited by 5

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1.

2 papers.

  1. 2023RAPL: A Relation-Aware Prototype Learning Approach for Few-Shot Document-Level Relation Extractioncited by 9
  2. 2024On the Robustness of Document-Level Relation Extraction Models to Entity Name Variationscited by 1