paper-with-me

홈 › Papers

Higher-order Coreference Resolution with Coarse-to-fine Inference

2018-04-15 · NAACL 2018 6 · Kenton Lee, Luheng He, Luke Zettlemoyer

We introduce a fully differentiable approximation to higher-order inference for coreference resolution. Our approach uses the antecedent distribution from a span-ranking architecture as an attention mechanism to iteratively refine span representations. This enables the model to softly consider multiple hops in the predicted clusters. To alleviate the computational cost of this iterative process, we introduce a coarse-to-fine approach that incorporates a less accurate but more efficient bilinear factor, enabling more aggressive pruning without hurting accuracy. Compared to the existing state-of-the-art span-ranking approach, our model significantly improves accuracy on the English OntoNotes benchmark, while being far more computationally efficient.

📄 PDF Abstract BibTeX arXiv:1804.05392

Code (5)

kentonl/e2e-coref 공식 구현 tf
Filter-Bubble/e2e-Dutch tf
bkntr/coref-ee tf
kkjawz/coref-ee tf
shayneobrien/coreference-resolution pytorch

Tasks

Coreference Resolution

Similar Papers 제목 키워드 기반

Revealing the Myth of Higher-Order Inference in Coreference Resolution

2020-09-25 · EMNLP 2020 11 · Liyan Xu, Jinho D. Choi

This paper analyzes the impact of higher-order inference (HOI) on the task of coreference resolution. HOI has been adapted by almost all recent coreference resolution models without taking much investigation on its true …

AvgClusteringcoreference-resolutionCoreference Resolution+1

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 …

coreference-resolutionCoreference ResolutionCross Document Coreference ResolutionNatural Language Understanding

End-to-end Deep Reinforcement Learning Based Coreference Resolution

2019-07-01 · ACL 2019 7 · Hongliang Fei, Xu Li, Dingcheng Li, Ping Li

Recent neural network models have significantly advanced the task of coreference resolution. However, current neural coreference models are usually trained with heuristic loss functions that are computed over a sequence …

coreference-resolutionCoreference ResolutionDeep Reinforcement Learningreinforcement-learning+2

End-to-end Neural Coreference Resolution Revisited: A Simple yet Effective Baseline

2021-07-04 · Tuan Manh Lai, Trung Bui, Doo Soon Kim

Since the first end-to-end neural coreference resolution model was introduced, many extensions to the model have been proposed, ranging from using higher-order inference to directly optimizing evaluation metrics using re…

coreference-resolutionCoreference Resolution

An End-to-End Approach for Full Bridging Resolution

2021-11-01 · ACL (CODI, CRAC) 2021 11 · Joseph Renner, Priyansh Trivedi, Gaurav Maheshwari, Rémi Gilleron 외

In this article, we describe our submission to the CODI-CRAC 2021 Shared Task on Anaphora Resolution in Dialogues – Track BR (Gold). We demonstrate the performance of an end-to-end transformer-based higher-order corefere…