Trainable Sentence Planning for Complex Information Presentations in Spoken Dialog Systems

Trainable Sentence Planning for Complex Information Presentation in Spoken Dialog Systems Amanda Stent Stony Brook University Stony Brook, NY 11794 U.S.A. stent@cs.sunysb.edu Rashmi Prasad University of Pennsylvania Philadelphia, PA 19104 U.S.A. rjprasad@linc.cis.upenn.edu Marilyn Walker University of Sheffield Sheffield S1 4DP U.K. M.A.Walker@sheffield.ac.uk Abstract A challenging problem for spoken dialog sys- tems is the design of utterance generation mod- ules that are fast, flexible and general, yet pro- duce high quality output in particular domains. A promising approach is trainable generation, which uses general-purpose linguistic knowledge automatically adapted to the application do- main. This paper presents a trainable sentence planner for the MATCH dialog system. We show that trainable sentence planning can pro- duce output comparable to that of MATCH’s template-based generator even for quite com- plex information presentations. 1 Introduction One very challenging problem for spoken dialog systems is the design of the utterance genera- tion module. This challenge arises partly from the need for the generator to adapt to many features of the dialog domain, user population, and dialog context. There are three possible approaches to gener- ating system utterances. The first is template- based generation, used in most dialog systems today. Template-based generation enables a programmer without linguistic training to pro- gram a generator that can efficiently produce high quality output specific to different dialog situations. Its drawbacks include the need to (1) create templates anew by hand for each ap- plication; (2) design and maintain a set of tem- plates that work well together in many dialog contexts; and (3) repeatedly encode linguistic constraints such as subject-verb agreement. The second approach is natural language gen- eration (NLG), which divides generation into: (1) text (or content) planning, (2) sentence planning, and (3) surface realization. NLG promises portability across domains and dialog contexts by using general rules for each genera- tion module. However, the quality of the output for a particular domain, or a particular dialog context, may be inferior to that of a template- based system unless domain-specific rules are developed or general rules are tuned for the par- ticular domain. Furthermore, full NLG may be too slow for use in dialog systems. A third, more recent, approach is trainable generation: techniques for automatically train- ing NLG modules, or hybrid techniques that adapt NLG modules to particular domains or user groups, e.g. (Langkilde, 2000; Mellish, 1998; Walker, Rambow and Rogati, 2002). Open questions about the trainable approach include (1) whether the output quality is high enough, and (2) whether the techniques work well across domains. For example, the training method used in SPoT (Sentence Planner Train- able), as described in (Walker, Rambow and Ro- gati, 2002), was only shown to work in the travel domain, for the information gathering phase of the dialog, and with simple content plans in- volving no rhetorical relations. This paper describes trainable sentence planning for information presentation in the MATCH (Multimodal Access To City Help) di- alog system (Johnston et al., 2002). We pro- vide evidence that the trainable approach is feasible by …

Content truncated to 500 words