Generating Statistical Language Models from Interpretation Grammars in Dialogue Systems

Generating statistical language models from interpretation grammars in dialogue systems Rebecca Jonson Dept. of Linguistics, G¨oteborg University and GSLT rj@ling.gu.se Abstract In this paper, we explore statistical lan- guage modelling for a speech-enabled MP3 player application by generating a corpus from the interpretation grammar written for the application with the Gram- matical Framework (GF) (Ranta, 2004). We create a statistical language model (SLM) directly from our interpretation grammar and compare recognition per- formance of this model against a speech recognition grammar compiled from the same GF interpretation grammar. The results show a relative Word Error Rate (WER) reduction of 37% for the SLM derived from the interpretation grammar while maintaining a low in-grammar WER comparable to that associated with the speech recognition grammar. From this starting point we try to improve our arti- ficially generated model by interpolating it with different corpora achieving great reduction in perplexity and 8% relative recognition improvement. 1 Introduction Ideally when building spoken dialogue systems, we would like to use a corpus of transcribed di- alogues corresponding to the specific task of the dialogue system, in order to build a statistical lan- guage model (SLM). However, it is rarely the case that such a corpus exists in the early stage of the development of a dialogue system. Collect- ing such a corpus and transcribing it is very time- consuming and delays the building of the actual dialogue system. An approach taken both in dialogue systems and dictation applications is to first write an in- terpretation grammar and from that generate an artificial corpus which is used as training corpus for the SLM (Raux et al, 2003; Pakhomov et al, 2001; Fosler-Lussier & Kuo, 2001). These mod- els obtained from grammars are not as good as the ones built from real data as the estimates are arti- ficial, lacking a real distribution. However, it is a quick way to get a dialogue system working with an SLM. When the system is up and running it is possible to collect real data that can be used to improve the model. We will explore this idea by generating a corpus from an interpretation gram- mar from one of our applications. A different approach is to compile the interpre- tation grammar into a speech recognition gram- mar as the Gemini and REGULUS compilers do (Rayner et al, 2000; Rayner et al, 2003). In this way it is assured that the linguistic coverage of the speech recognition and interpretation are kept in sync. Such an approach enables us to interpret all that we can recognize and the other way round. In the European-funded project TALK the Grammat- ical Framework (Ranta, 2005) has been extended with such a facility that compiles GF grammars into speech recognition grammars in Nuance GSL format (www.nuance.com). Speech recognition for commercial dialogue systems has focused on grammar-based ap- proaches despite the fact that statistical language models seem to have a better overall performance (Gorrell et al, 2002). This probably depends on the time-consuming work of collecting …

Content truncated to 500 words