Spoken Dialogue Understanding and Local Context.
Peter A. Heeman · 1994
Spoken dialogue poses many new problems to researchers in the field of computational linguistics. In particular, conversants must detect and correct speech repairs, segment a turn into individual utterances, and identify discourse markers. These problems are interrelated. For instance, there are some lexical items whose role in an utterance can be ambiguous: they can act as discourse markers, signal a speech repair, or even be part of the content of an utterance unit. So, these issues must be addressed together. The resolution of these problems will allow a basic understanding of how a speaker's turn can be broken down into individual contributions to the dialogue. We propose that this resolution must be and can be done using local context. They do not require a full understanding of the dialogue so far, nor, in most cases, a deep understanding of the current turn. Resolving these issues locally also means they can be resolved for the most part before later processing, and so will make a natural language understanding system more robust and able to deal with the unconstrained nature of spoken dialogue.