A Neural Network for Coordination Boundary Prediction

TL;DR

This paper introduces a neural network model that predicts coordination boundaries in sentences by leveraging conjunct similarity and sentence coherence, trained solely on Treebank annotations, and outperforms existing systems.

Contribution

It presents a novel neural network approach utilizing LSTMs for coordination boundary prediction, trained without external resources, and demonstrates improved accuracy over state-of-the-art methods.

Findings

Improved coordination boundary prediction on PTB dataset

Enhanced performance on Genia corpus

Effective use of conjunct similarity and sentence coherence signals

Abstract

We propose a neural-network based model for coordination boundary prediction. The network is designed to incorporate two signals: the similarity between conjuncts and the observation that replacing the whole coordination phrase with a conjunct tends to produce a coherent sentences. The modeling makes use of several LSTM networks. The model is trained solely on conjunction annotations in a Treebank, without using external resources. We show improvements on predicting coordination boundaries on the PTB compared to two state-of-the-art parsers; as well as improvement over previous coordination boundary prediction systems on the Genia corpus.