Robust processing of situated spoken dialogue

Spoken dialogue is notoriously hard to process with standard language processing technologies. Dialogue systems must indeed meet two major chal- lenges. First, natural spoken dialogue is replete with disfluent, partial, elided or ungrammatical utterances. Second, speech recognition remains a highly error- prone task, especially for complex, open-ended domains. We present an inte- grated approach for addressing these two issues, based on a robust incremental parser. The parser takes word lattices as input and is able to handle ill-formed and misrecognised utterances by selectively relaxing its set of grammatical rules. The choice of the most relevant interpretation is then realised via a discrimina- tive model augmented with contextual information. The approach is fully im- plemented in a dialogue system for autonomous robots. Evaluation results on a Wizard of Oz test suite demonstrate very significant improvements in accuracy and robustness compared to the baseline.