EUROSPEECH 2001 Scandinavia
7th European Conference on Speech Communication and Technology

Aalborg, Denmark
September 3-7, 2001


Hybrid Natural Language Generation for Spoken Dialogue Systems

Michel Galley, Eric Fosler-Lussier, Alexandros Potamianos

Lucent Technologies, USA

The natural language generation component of most dialogue systems is based on templates. Template-based generators are hard to maintain and reuse, and the sentences they produce lack the variability and robustness needed by conversational systems. In this paper, a flexible and domain-independent natural language generator for spoken dialogue systems is proposed which combines fixed surface expressions with freely generated text. The generation algorithm follows a hybrid approach, combining finite state machine (FSM) grammars and corpus-based language models. In this approach, the FSM grammar (a reversible parser grammar) is constrained by a word and concept n-gram that takes terminals and non-terminal co-occurrences into account. The n-gram grammar helps prevent inappropriate derivations, therefore improving the quality of the generated texts. The proposed algorithm achieves faster than real-time performance because of the limited number of derivations.

Full Paper

Bibliographic reference.  Galley, Michel / Fosler-Lussier, Eric / Potamianos, Alexandros (2001): "Hybrid natural language generation for spoken dialogue systems", In EUROSPEECH-2001, 1735-1738.