Segmentation Approach for Coreference Resolution Task

TL;DR

This paper introduces a novel coreference resolution method that encodes all cluster members simultaneously using span position embeddings and BERT, aiming to improve long-distance relation detection.

Contribution

It proposes a new approach that resolves all coreference mentions in one pass by embedding cluster member positions, enhancing long-distance relation capture.

Findings

Preliminary results show promise despite not surpassing state-of-the-art.

The method effectively captures long-distance coreference relations.

Using BERT and span position embeddings improves cluster relation modeling.

Abstract

In coreference resolution, it is important to consider all members of a coreference cluster and decide about all of them at once. This technique can help to avoid losing precision and also in finding long-distance relations. The presented paper is a report of an ongoing study on an idea which proposes a new approach for coreference resolution which can resolve all coreference mentions to a given mention in the document in one pass. This has been accomplished by defining an embedding method for the position of all members of a coreference cluster in a document and resolving all of them for a given mention. In the proposed method, the BERT model has been used for encoding the documents and a head network designed to capture the relations between the embedded tokens. These are then converted to the proposed span position embedding matrix which embeds the position of all coreference mentions in the document. We tested this idea on CoNLL 2012 dataset and although the preliminary results from this method do not quite meet the state-of-the-art results, they are promising and they can capture features like long-distance relations better than the other approaches.