Robust processing of situated spoken dialogue
Tagungsband der GSCL Jahrestagung, 2009
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 disï¬uent, 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 signiï¬cant improvements in accuracy and robustness compared to the baseline.