Paper: Joint Decoding of Tree Transduction Models for Sentence Compression

ACL ID D14-1195
Title Joint Decoding of Tree Transduction Models for Sentence Compression
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2014
Authors

In this paper, we provide a new method for decoding tree transduction based sentence compression models augmented with lan- guage model scores, by jointly decoding two components. In our proposed so- lution, rich local discriminative features can be easily integrated without increasing computational complexity. Utilizing an unobvious fact that the resulted two com- ponents can be independently decoded, we conduct efficient joint decoding based on dual decomposition. Experimental results show that our method outperforms tradi- tional beam search decoding and achieves the state-of-the-art performance.