paper-with-me

홈 › Papers

Sequential Cross-Document Coreference Resolution

2021-04-17 · EMNLP 2021 11 · Emily Allaway, Shuai Wang, Miguel Ballesteros

Relating entities and events in text is a key component of natural language understanding. Cross-document coreference resolution, in particular, is important for the growing interest in multi-document analysis tasks. In this work we propose a new model that extends the efficient sequential prediction paradigm for coreference resolution to cross-document settings and achieves competitive results for both entity and event coreference while provides strong evidence of the efficacy of both sequential models and higher-order inference in cross-document settings. Our model incrementally composes mentions into cluster representations and predicts links between a mention and the already constructed clusters, approximating a higher-order model. In addition, we conduct extensive ablation studies that provide new insights into the importance of various inputs and representation types in coreference.

📄 PDF Abstract BibTeX arXiv:2104.08413

Code (0)

등록된 구현이 없습니다.

Tasks

coreference-resolutionCoreference ResolutionCross Document Coreference ResolutionNatural Language Understanding

Similar Papers 제목 키워드 기반

Cross-document Coreference Resolution over Predicted Mentions

2021-06-02 · Findings (ACL) 2021 8 · Arie Cattan, Alon Eirew, Gabriel Stanovsky, Mandar Joshi 외

Coreference resolution has been mostly investigated within a single document scope, showing impressive progress in recent years based on end-to-end models. However, the more challenging task of cross-document (CD) corefe…

coreference-resolutionCoreference ResolutionCross Document Coreference Resolution

Event Coreference Resolution Using Neural Network Classifiers

2018-10-09 · Arun Pandian, Lamana Mulaffer, Kemal Oflazer, Amna AlZeyara

This paper presents a neural network classifier approach to detecting both within- and cross- document event coreference effectively using only event mention based features. Our approach does not (yet) rely on any event …

coreference-resolutionCoreference ResolutionCross Document Coreference ResolutionEvent Coreference Resolution+1

Improving Event Coreference Resolution by Modeling Correlations between Event Coreference Chains and Document Topic Structures

2018-07-01 · ACL 2018 7 · Prafulla Kumar Choubey, Ruihong Huang

This paper proposes a novel approach for event coreference resolution that models correlations between event coreference chains and document topical structures through an Integer Linear Programming formulation. We explic…

coreference-resolutionCoreference ResolutionEvent Coreference ResolutionQuestion Answering

Streamlining Cross-Document Coreference Resolution: Evaluation and Modeling

2020-09-23 · Arie Cattan, Alon Eirew, Gabriel Stanovsky, Mandar Joshi 외

Recent evaluation protocols for Cross-document (CD) coreference resolution have often been inconsistent or lenient, leading to incomparable results across works and overestimation of performance. To facilitate proper fut…

coreference-resolutionCoreference ResolutionCross Document Coreference ResolutionEntity Cross-Document Coreference Resolution+1

Sieve-based Coreference Resolution in the Biomedical Domain

2016-03-11 · LREC 2016 5 · Dane Bell, Gus Hahn-Powell, Marco A. Valenzuela-Escárcega, Mihai Surdeanu

We describe challenges and advantages unique to coreference resolution in the biomedical domain, and a sieve-based architecture that leverages domain knowledge for both entity and event coreference resolution. Domain-gen…

coreference-resolutionCoreference ResolutionEvent Coreference ResolutionEvent Extraction