Contrastive Representation Learning for Cross-Document Coreference Resolution of Events and Entities
Year: 2022
Type: conference-paper
Abstract: Identifying related entities and events within and across documents is fundamental to natural language understanding.We present an approach to entity and event coreference resolution utilizing contrastive representation learning.Earlier state-of-the-art methods have formulated this problem as a binary classification problem and leveraged large transformers in a cross-encoder architecture to achieve their results.For large collections of documents and corresponding set of n mentions, the necessity of performing n 2 transformer computations in these earlier approaches can be computationally intensive.We show that it is possible to reduce this burden by applying contrastive learning techniques that only require n transformer computations at inference time.Our method achieves state-of-the-art results on a number of key metrics on the ECB+ corpus and is competitive on others.
Authors: Benjamin Hsu, Graham Horwood
Institution: Amazon (United States)
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4287854772