CLMay 28, 2018

Resolving Event Coreference with Supervised Representation Learning and Clustering-Oriented Regularization

arXiv:1805.10985v11108 citations
Originality Incremental advance
AI Analysis

This addresses event coreference resolution for natural language processing, but it is incremental as it builds on existing representation learning and clustering methods.

The paper tackled event coreference resolution by proposing a neural network with Clustering-Oriented Regularization to learn embeddings for clustering, achieving better results than models requiring more pre-annotated information on the ECB+ corpus.

We present an approach to event coreference resolution by developing a general framework for clustering that uses supervised representation learning. We propose a neural network architecture with novel Clustering-Oriented Regularization (CORE) terms in the objective function. These terms encourage the model to create embeddings of event mentions that are amenable to clustering. We then use agglomerative clustering on these embeddings to build event coreference chains. For both within- and cross-document coreference on the ECB+ corpus, our model obtains better results than models that require significantly more pre-annotated information. This work provides insight and motivating results for a new general approach to solving coreference and clustering problems with representation learning.

Code Implementations1 repo
Foundations

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

Your Notes