Labeling Gaps Between Words: Recognizing Overlapping Mentions with Mention Separators

TL;DR

This paper introduces a novel model for recognizing overlapping mentions in text using mention separators and a multigraph representation, enabling efficient inference and improving recognition accuracy.

Contribution

The paper presents a new concept of mention separators and a multigraph-based model that effectively captures mention overlaps with efficient inference capabilities.

Findings

Effective recognition of overlapping mentions demonstrated on standard datasets

The proposed model outperforms previous approaches in accuracy

Theoretical analysis highlights differences with existing models

Abstract

In this paper, we propose a new model that is capable of recognizing overlapping mentions. We introduce a novel notion of mention separators that can be effectively used to capture how mentions overlap with one another. On top of a novel multigraph representation that we introduce, we show that efficient and exact inference can still be performed. We present some theoretical analysis on the differences between our model and a recently proposed model for recognizing overlapping mentions, and discuss the possible implications of the differences. Through extensive empirical analysis on standard datasets, we demonstrate the effectiveness of our approach.