Sentence Compression as Tree Transduction
This work addresses sentence compression for natural language processing applications, representing an incremental advancement with a novel method for a known bottleneck.
The paper tackles sentence compression by proposing a tree-to-tree transduction method based on synchronous tree substitution grammar, which allows local distortion of tree topology to capture structural mismatches, and it shows significant improvements over a state-of-the-art model in experimental results.
This paper presents a tree-to-tree transduction method for sentence compression. Our model is based on synchronous tree substitution grammar, a formalism that allows local distortion of the tree topology and can thus naturally capture structural mismatches. We describe an algorithm for decoding in this framework and show how the model can be trained discriminatively within a large margin framework. Experimental results on sentence compression bring significant improvements over a state-of-the-art model.