Within-Document Event Coreference with BERT-Based Contextualized Representations
Shafiuddin Rehan Ahmed, James H. Martin

TL;DR
This paper introduces a BERT-based approach for within-document event coreference, achieving state-of-the-art results by combining contextualized representations with neural classification and clustering.
Contribution
The study demonstrates the effectiveness of pretrained BERT representations in improving within-document event coreference performance.
Findings
Achieved state-of-the-art results on two standard datasets.
Established a new benchmark on a newer dataset.
Showed that BERT-based representations enhance event coreference clustering.
Abstract
Event coreference continues to be a challenging problem in information extraction. With the absence of any external knowledge bases for events, coreference becomes a clustering task that relies on effective representations of the context in which event mentions appear. Recent advances in contextualized language representations have proven successful in many tasks, however, their use in event linking been limited. Here we present a three part approach that (1) uses representations derived from a pretrained BERT model to (2) train a neural classifier to (3) drive a simple clustering algorithm to create coreference chains. We achieve state of the art results with this model on two standard datasets for within-document event coreference task and establish a new standard on a third newer dataset.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Natural Language Processing Techniques · Data Quality and Management
MethodsLinear Layer · Linear Warmup With Linear Decay · Softmax · Adam · Multi-Head Attention · Attention Dropout · Weight Decay · Residual Connection · Attention Is All You Need · Dropout
