Minimizing Cumulative

Cumulative error limits the usefulness of context in applications utilizing contextual information. It is especially a problem in spontaneous speech systems where unexpected input, out-of-domain utterances and missing information are hard to t into the standard structure of the contextual model. In this paper we discuss how our approaches to recognizing speech acts address the problem of cumulative error. We demonstrate the advantage of the proposed approaches over those that do not address the problem of cumulative error. The experiments are conducted in the context of Enthusiast, a large Spanish-to-English speech-to-speech translation system in the appointment scheduling domain 10, 5, 11]. 1 The Cumulative Error Problem To interpret natural language, it is necessary to take context into account. However , taking context into account can also generate new problems, such as those arising because of cumulative error. Cumulative error is introduced when an incorrect hypothesis is chosen and incorporated into the context, thus providing an inaccurate context from which subsequent context-based predictions are made. For example, in Enthusiast, a large Spanish-to-English speech-to-speech translation system in the appointment scheduling domain 10, 5, 11], we model the discourse context using speech acts to represent the functions of dialogue utterances. Speech act selection is strongly related to the task of determining how the current input utterance relates to the discourse context. When, for instance , a plan-based discourse processor is used to recognize speech acts, the discourse processor computes a chain of inferences for the current input utterance , and attaches it to the current plan tree. The location of the attachment determines which speech act is assigned to the input utterance. Typically an input utterance can be associated with more than one inference chain, representing diierent possible speech acts which could be performed by the utterance out of context. Focusing heuristics are used to rank the diierent inference chains and choose the one which attaches most coherently to the discourse context 3, 8]. However, since heuristics can make wrong predictions, the speech act may be