Syntactic annotation of spontaneous speech: application to call-center conversation data

Both frameworks are based on the automatic semantic analysis of Human-Human spoken conversations. The semantic interpretation of a spoken utterance can be split into a two-level process: a tagging process projecting lexical items into basic conceptual constituents and a composition process that takes as input these basic constituents and combine them in a possibly complex semantic interpretation of the utterance, represented, for example, as a set of semantic Frames. Various methods, reviewed in [3], have been proposed for both levels of this process, from statistical tagging approaches to parsing methods. Syntactic information is useful to perform such an understanding process: at the concept level, syntax can help reducing the ambiguity through semantic role labelling; at the semantic Frame level, syntactic dependencies can be projected into semantic dependencies to obtain structured semantic objects. Despite its usefulness, syntactic parsing is not always considered when building a Spoken Language Understanding (SLU) system dedicated to process spontaneous speech because of two main issues: firstly transcriptions obtained through an Automatic Speech Recognition (ASR) process contain errors, the amount of errors increasing with the level of spontaneity in speech; secondly, spontaneous speech transcriptions are often difficult to parse using a grammar developed for written text due to the specificities of spontaneous speech syntax (agrammaticality, disfluences such as repairs, false starts or repetitions). The first issue is currently tackled in the DECODA project with the use of methods dealing with ambiguous inputs, such as word lattices produced by an Automatic Speech Recognition (ASR) system. The second issue is the target of this paper.