Towards statistical paraphrase generation: preliminary evaluations of grammaticality

Stephen Wan, Mark Dras, Robert Dale, Cécile Paris

    Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review

    Abstract

    Summary sentences are often paraphrases of existing sentences. They may be made up of recycled fragments of text taken from important sentences in an input document. We investigate the use of a statistical sentence generation technique that recombines words probabilistically in order to create new sentences. Given a set of event-related sentences, we use an extended version of the Viterbi algorithm which employs dependency relation and bigram probabilities to find the most probable summary sentence. Using precision and recall metrics for verb arguments as a measure of grammaticality, we find that our system performs better than a bigram baseline, producing fewer spurious verb arguments.
    Original languageEnglish
    Title of host publicationProceedings of the Third International Workshop on Paraphrasing (IWP2005)
    EditorsMark Dras, Kazuhide Yamamoto
    Place of PublicationJapan
    PublisherAsian Federation of Natural Language Processing
    Pages88-95
    Number of pages8
    Publication statusPublished - 2005
    EventInternational Workshop on Paraphrasing (3rd : 2005) - Jeju Island, South Korea
    Duration: 14 Oct 200514 Oct 2005

    Workshop

    WorkshopInternational Workshop on Paraphrasing (3rd : 2005)
    CityJeju Island, South Korea
    Period14/10/0514/10/05

    Fingerprint Dive into the research topics of 'Towards statistical paraphrase generation: preliminary evaluations of grammaticality'. Together they form a unique fingerprint.

    Cite this