CLApr 17, 2021

Sequential Cross-Document Coreference Resolution

arXiv:2104.08413v1665 citations
AI Analysis

This work addresses multi-document analysis tasks in natural language understanding, with incremental improvements in coreference resolution.

The paper tackles cross-document coreference resolution by proposing a sequential prediction model that extends to cross-document settings, achieving competitive results for both entity and event coreference.

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 provides 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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes