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

Proceedings of the 43rd Annual Meeting of the ACL, pages 247–254, Ann Arbor, June 2005. c⃝2005 Association for Computational Linguistics Towards Finding and Fixing Fragments: Using ML to Identify Non-Sentential Utterances and their Antecedents in Multi-Party Dialogue David Schlangen Department of Linguistics University of Potsdam P.O. Box 601553 D-14415 Potsdam — Germany das@ling.uni-potsdam.de Abstract Non-sentential utterances (e.g., short- answers as in “Who came to the party?”— “Peter.”) are pervasive in dialogue. As with other forms of ellipsis, the elided ma- terial is typically present in the context (e.g., the question that a short answer an- swers). We present a machine learning approach to the novel task of identifying fragments and their antecedents in multi- party dialogue. We compare the perfor- mance of several learning algorithms, us- ing a mixture of structural and lexical fea- tures, 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). 1 Introduction Non-sentential utterances (NSUs) as in (1) are per- vasive in dialogue: recent studies put the proportion of such utterances at around 10% across different types of dialogue (Fern´andez and Ginzburg, 2002; Schlangen and Lascarides, 2003). (1) a. A: Who came to the party? B: Peter. (= Peter came to the party.) b. A: I talked to Peter. B: Peter Miller? (= Was it Peter Miller you talked to?) c. A: Who was this? Peter Miller? (= Was this Peter Miller? Such utterances pose an obvious problem for natural language processing applications, namely that the intended information (in (1-a)-B a proposition) has to be recovered from the uttered information (here, an NP meaning) with the help of information from the context. While some systems that automatically resolve such fragments have recently been developed (Schlangen and Lascarides, 2002; Fern´andez et al., 2004a), they have the drawback that they require “deep” linguistic processing (full parses, and also in- formation about discourse structure) and hence are not very robust. We have defined a well-defined subtask of this problem, namely identifying frag- ments (certain kinds of NSUs, see below) and their antecedents (in multi-party dialogue, in our case), and present a novel machine learning approach to it, which we hypothesise will be useful for tasks such as automatic meeting summarisation.1 The remainder of this paper is structured as fol- lows. In the next section we further specify the task and different possible approaches to it. We then de- scribe the corpus we used, some of its characteris- tics with respect to fragments, and the features we extracted from it for machine learning. Section 4 describes our experimental settings and reports the results. After a comparison to related work in Sec- tion 5, we close with a conclusion and some further 1(Zechner and Lavie, 2001) describe a related task, linking questions and answers, and evaluate its usefulness in the context of automatic summarisation; see Section 5. 247 work …

Content truncated to 500 words