Learning Global Features for Coreference Resolution

Abstract

There is compelling evidence that coreference prediction would benefit from modeling global information about entity-clusters. Yet, state-of-the-art performance can be achieved with systems treating each mention prediction independently, which we attribute to the inherent difficulty of crafting informative cluster-level features. We instead propose to use recurrent neural networks (RNNs) to learn latent, global representations of entity clusters directly from their mentions. We show that such representations are especially useful for the prediction of pronominal mentions, and can be incorporated into an end-to-end coreference system that outperforms the state of the art without requiring any additional search.

Accepted to NAACL 2016

References in corpus (6)

• Sequence to Sequence Learning with Neural Networks
• Recurrent Neural Network Regularization
• Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
• Transition-Based Dependency Parsing with Stack Long Short-Term Memory
• Search-based Structured Prediction
• rnn : Recurrent Library for Torch

Cited by in corpus (11)

• Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction
• A Neural Language Model for Dynamically Representing the Meanings of Unknown Words and Entities in a Discourse
• Dynamic Entity Representations in Neural Language Models
• Reference-Aware Language Models
• RGAT: A Deeper Look into Syntactic Dependency Information for Coreference Resolution
• Event Coreference Resolution by Iteratively Unfolding Inter-dependencies among Events
• Mind the GAP: A Balanced Corpus of Gendered Ambiguous Pronouns
• Syntactic Scaffolds for Semantic Structures
• Look Again at the Syntax: Relational Graph Convolutional Network for Gendered Ambiguous Pronoun Resolution
• Use Generalized Representations, But Do Not Forget Surface Features
• Neural Cross-Lingual Coreference Resolution and its Application to Entity Linking