Paper: Sentence Compression with Joint Structural Inference

ACL ID W13-3508
Title Sentence Compression with Joint Structural Inference
Venue International Conference on Computational Natural Language Learning
Session Main Conference
Year 2013

Sentence compression techniques often assemble output sentences using frag- ments of lexical sequences such as n- grams or units of syntactic structure such as edges from a dependency tree repre- sentation. We present a novel approach for discriminative sentence compression that unifies these notions and jointly pro- duces sequential and syntactic represen- tations for output text, leveraging a com- pact integer linear programming formula- tion to maintain structural integrity. Our supervised models permit rich features over heterogeneous linguistic structures and generalize over previous state-of-the- art approaches. Experiments on corpora featuring human-generated compressions demonstrate a 13-15% relative gain in 4- gram accuracy over a well-studied lan- guage model-based compression sy...