Title | Statistically Generated Summary Sentences: A Preliminary Evaluation using a Dependency Relation Precision Metric |
Publication Type | Conference Paper |
Year of Publication | 2005 |
Authors | Wan S, Dras M, Dale R, Paris C |
Conference Name | Corpus Linguistics 2005 Workshop on Using Corpora for Natural Language Generation |
Conference Location | Birmingham |
Abstract | Often in summarisation, we are required to generate a summary sentence that incorporates the important elements of a related set of sentences. In this paper, we do this by using a statistical approach that combines models of n-grams and dependency structure. The approach is one in which words are recycled and re-combined to forma new sentence, one that is grammatical and that reflects the content of the source material. We use an extension to the Viterbi algorithm that generates a sequence that is not only the best n-gram word sequence, but also best replicates component dependency structures taken from the source text. In this paper, we describe the extension and outline a preliminary evaluation that measures dependency structure recall and precision in the generated string. We find that our approach achieves higher precision when compared to a bigram generator. |
URL | http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.158.8142&rep=rep1&type=pdf |
- Log in or register to post comments
- Google Scholar