Non-Sentential Utterances in Dialogue: Experiments in Classification and Interpretation

Non-sentential utterances (NSUs) are utterances that lack a complete sentential form but whose meaning can be inferred from the dialogue context, such as “OK”, “where?”, “probably at his apartment”. The interpretation of non-sentential utterances is an important problem in computational linguistics since they constitute a frequent phenomena in dialogue and they are intrinsically context-dependent. The interpretation of NSUs is the task of retrieving their full semantic content from their form and the dialogue context. NSUs also come in a wide variety of forms and functions and classifying them in the right category is a prerequisite to their interpretation. The first half of this thesis is devoted to the NSU classification task. Our work builds upon Fernández et al. (2007) which present a series of machine-learning experiments on the classification of NSUs. We extended their approach with a combination of new features and semi-supervised learning techniques. The empirical results presented in this thesis show a modest but significant improvement over the state-of-the-art classification performance. The consecutive, yet independent, problem is how to infer an appropriate semantic representation of such NSUs on the basis of the dialogue context. Fernández (2006) formalizes this task in terms of “resolution rules” built on top of the Type Theory with Records (TTR), a theoretical framework for dialogue context modeling (Ginzburg, 2012). We argue that logic-based formalisms, such as TTR, have a number of shortcomings when dealing with conversational data, which often include partially observable knowledge and non-deterministic phenomena. An alternative to address these issues is to rely on probabilistic modeling of the dialogue context. Our work is focused on the reimplementation of the resolution rules from Fernández (2006) with a probabilistic account of the dialogue state. The probabilistic rules formalism (Lison, 2014) is particularly suited for this task because, similarly to the framework developed by Ginzburg (2012) and Fernández (2006), it involves the specification of update rules on the variables of the dialogue state to capture the dynamics of the conversation. However, the probabilistic rules can also encode probabilistic knowledge, thereby providing a principled account of ambiguities in the NSU resolution process. In the second part of this thesis, we present our proof-of-concept framework for NSU resolution using probabilistic rules.