DeepAI
Log In Sign Up

End-to-end Neural Coreference Resolution

07/21/2017
by   Kenton Lee, et al.
0

We introduce the first end-to-end coreference resolution model and show that it significantly outperforms all previous work without using a syntactic parser or hand-engineered mention detector. The key idea is to directly consider all spans in a document as potential mentions and learn distributions over possible antecedents for each. The model computes span embeddings that combine context-dependent boundary representations with a head-finding attention mechanism. It is trained to maximize the marginal likelihood of gold antecedent spans from coreference clusters and is factored to enable aggressive pruning of potential mentions. Experiments demonstrate state-of-the-art performance, with a gain of 1.5 F1 on the OntoNotes benchmark and by 3.1 F1 using a 5-model ensemble, despite the fact that this is the first approach to be successfully trained with no external resources.

READ FULL TEXT

page 1

page 2

page 3

page 4

05/13/2018

Neural Coreference Resolution with Deep Biaffine Attention by Joint Mention Detection and Mention Clustering

Coreference resolution aims to identify in a text all mentions that refe...
06/02/2021

Cross-document Coreference Resolution over Predicted Mentions

Coreference resolution has been mostly investigated within a single docu...
10/31/2020

Neural Coreference Resolution for Arabic

No neural coreference resolver for Arabic exists, in fact we are not awa...
05/02/2018

Constituency Parsing with a Self-Attentive Encoder

We demonstrate that replacing an LSTM encoder with a self-attentive arch...
09/09/2021

Word-Level Coreference Resolution

Recent coreference resolution models rely heavily on span representation...
04/30/2020

A Span-based Linearization for Constituent Trees

We propose a novel linearization of a constituent tree, together with a ...
04/15/2018

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

We introduce a fully differentiable approximation to higher-order infere...