Coreference Resolution System for Indonesian Text with Mention Pair Method and Singleton Exclusion using Convolutional Neural Network

TL;DR

This paper introduces a deep neural network-based coreference resolution system for Indonesian text that leverages mention pair methods, word embeddings, CNNs, and singleton exclusion to improve performance over existing systems.

Contribution

It is the first to apply deep neural networks with mention pair methods and singleton exclusion for Indonesian coreference resolution, outperforming previous lexical and syntactic feature-based systems.

Findings

Achieved 75.95% F1 score with gold singleton classifier

Outperformed existing state-of-the-art system

Demonstrated effectiveness of CNN and singleton exclusion in Indonesian coreference resolution

Abstract

Neural network has shown promising performance on coreference resolution systems that uses mention pair method. With deep neural network, it can learn hidden and deep relations between two mentions. However, there is no work on coreference resolution for Indonesian text that uses this learning technique. The state-of-the-art system for Indonesian text only states the use of lexical and syntactic features can improve the existing coreference resolution system. In this paper, we propose a new coreference resolution system for Indonesian text with mention pair method that uses deep neural network to learn the relations of the two mentions. In addition to lexical and syntactic features, in order to learn the representation of the mentions words and context, we use word embeddings and feed them to Convolutional Neural Network (CNN). Furthermore, we do singleton exclusion using singleton classifier component to prevent singleton mentions entering any entity clusters at the end. Achieving 67.37% without singleton exclusion, 63.27% with trained singleton classifier, and 75.95% with gold singleton classifier on CoNLL average F1 score, our proposed system outperforms the state-of-the-art system.