A Neural Network for Coordination Boundary Prediction
This work addresses a specific parsing challenge for natural language processing, with incremental improvements in accuracy.
The paper tackles the problem of predicting coordination boundaries in sentences by proposing a neural network model that uses similarity between conjuncts and phrase replacement coherence, achieving improvements over state-of-the-art parsers on the PTB and Genia corpus.
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.