Can Syntax Help? Improving an LSTM-based Sentence Compression Model for New Domains

In this paper, we study how to improve the domain adaptability of a deletion-based Long Short-Term Memory (LSTM) neural network model for sentence compression. We hypothesize that syntactic information helps in making such models more robust across domains. We propose two major changes to the model: using explicit syntactic features and introducing syntactic constraints through Integer Linear Programming (ILP). Our evaluation shows that the proposed model works better than the original model as well as a traditional non-neural-network-based model in a cross-domain setting.

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Sentence Compression Google Dataset BiLSTM F1 0.8 # 6
CR 0.43 # 1


No methods listed for this paper. Add relevant methods here