Year: 2021
Type: conference-paper
Abstract: 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 providing 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.
Authors: Emily Allaway, Shuai Wang, Miguel Ballesteros
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W3153553531