Searching for grammaticality: Propagating dependencies in the Viterbi algorithm

In many text-to-text generation scenarios (for instance, summarisation), we encounter human-authored sentences that could be composed by recycling portions of related sentences to form new sentences. In this paper, we couch the generation of such sentences as a search problem. We investigate a statistical sentence generation method which recombines words to form new sentences. We propose an extension to the Viterbi algorithm designed to improve the grammaticality of generated sentences. Within a statistical framework, the extension favours those partially generated strings with a probable dependency tree structure. Our preliminary evaluations show that our approach generates less fragmented text than a bigram baseline.