Sentence Compression with Joint Structural Inference
Kapil Thadani, Kathleen R. McKeown · 2013
Sentence compression techniques often assemble output sentences using fragments of lexical sequences such as n-grams or units of syntactic structure such as edges from a dependency tree representation. We present a novel approach for discriminative sentence compression that unifies these notions and jointly produces sequential and syntactic representations for output text, leveraging a compact integer linear programming formulation to maintain structural integrity. Our supervised models permit rich features over heterogeneous linguistic structures and generalize over previous state-of-theart approaches. Experiments on corpora featuring human-generated compressions demonstrate a 13-15 % relative gain in 4-gram accuracy over a well-studied language model-based compression system. 1