mlsanityData to 7 Oct 2026

Neural Models for Reasoning over Multiple Mentions using Coreference

arXiv 1804.05922 ↗First posted 16 Apr 2018cs.CL cs.LGcited by 27

Not on the map. Why?

Abstract (arXiv)

Many problems in NLP require aggregating information from multiple mentions of the same entity which may be far apart in the text. Existing Recurrent Neural Network (RNN) layers are biased towards short-term dependencies and hence not suited to such tasks. We present a recurrent layer which is instead biased towards coreferent dependencies. The layer uses coreference annotations extracted from an external system to connect entity mentions belonging to the same cluster. Incorporating this layer into a state-of-the-art reading comprehension model improves performance on three datasets -- Wikihop, LAMBADA and the bAbi AI tasks -- with large gains when training data is scarce.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 8; 2023: 3; 2024: 3; 2025: 1; 2026: 1.

27 papers.

Sort:

By area:

  1. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 170
  2. 2022What Artificial Neural Networks Can Tell Us About Human Language Acquisitioncited by 97
  3. 2021Entity Structure Within and Throughout: Modeling Mention Dependencies for Document-Level Relation Extractioncited by 68
  4. 2021Word-Level Coreference Resolutioncited by 40
  5. 2021Decomposing Complex Questions Makes Multi-Hop QA Easier and More Interpretablecited by 35
  6. 2021SIRE: Separate Intra- and Inter-sentential Reasoning for Document-level Relation Extractioncited by 30
  7. 2021On Generalization in Coreference Resolutioncited by 24
  8. 2021WEC: Deriving a Large-scale Cross-document Event Coreference dataset from Wikipediacited by 23
  9. 2024Maverick: Efficient and Accurate Coreference Resolution Defying Recent Trendscited by 19
  10. 2021Focus on what matters: Applying Discourse Coherence Theory to Cross Document Coreferencecited by 16
  11. 2021SciCo: Hierarchical Cross-Document Coreference for Scientific Conceptscited by 14
  12. 2022From Easy to Hard: Two-stage Selector and Reader for Multi-hop Question Answeringcited by 12
15 more
  1. 2022Cross-document Event Coreference Search: Task, Dataset and Modelingcited by 12
  2. 2022Contrastive Representation Learning for Cross-Document Coreference Resolution of Events and Entitiescited by 10
  3. 2022Lexical Generalization Improves with Larger Models and Longer Trainingcited by 9
  4. 2024Major Entity Identification: A Generalizable Alternative to Coreference Resolutioncited by 9
  5. 2022Locate Then Ask: Interpretable Stepwise Reasoning for Multi-hop Question Answeringcited by 6
  6. 2021Memory Augmented Sequential Paragraph Retrieval for Multi-hop Question Answeringcited by 4
  7. 2021Interactive Machine Comprehension with Dynamic Knowledge Graphscited by 2
  8. 2022Ask to Understand: Question Generation for Multi-hop Question Answeringcited by 2
  9. 2022Discourse-Aware Graph Networks for Textual Logical Reasoningcited by 2
  10. 2021ClueReader: Heterogeneous Graph Attention Network for Multi-hop Machine Reading Comprehensioncited by 1
  11. 2023Graph Attention with Hierarchies for Multi-hop Question Answeringcited by 1
  12. 2023Ensemble Transfer Learning for Multilingual Coreference Resolutioncited by 0
  13. 2023Perturbation-based Active Learning for Question Answeringcited by 0
  14. 2025Benchmarking Gaslighting Attacks Against Speech Large Language Modelscited by 0
  15. 2026Learning Complementary Action Modeling from Automotive Maintenance Instructionscited by 0