Towards Finding and Fixing Fragments-Using ML to Identify Non-Sentential Utterances and their Antecedents in Multi-Party Dialogue

Non-sentential utterances (e.g., shortanswers as in “Who came to the party?”— “Peter.”) are pervasive in dialogue. As with other forms of ellipsis, the elided material is typically present in the context (e.g., the question that a short answer answers). We present a machine learning approach to the novel task of identifying fragments and their antecedents in multiparty dialogue. We compare the performance of several learning algorithms, using a mixture of structural and lexical features, and show that the task of identifying antecedents given a fragment can be learnt successfully (f(0.5) = .76); we discuss why the task of identifying fragments is harder (f(0.5) = .41) and finally report on a combined task (f(0.5) = .38).