Towards Automatic Generation of Natural Language Generation Systems

Towards Automatic Generation of Natural Language Generation Systems John Chen∗, Srinivas Bangalore†, Owen Rambow∗, and Marilyn A. Walker† Columbia University∗ AT&T Labs–Research† New York, NY 10027 Florham Park, NJ 07932 {jchen,rambow}@cs.columbia.edu {srini,walker}@research.att.com Abstract Systems that interact with the user via natural language are in their infancy. As these systems mature and become more complex, it would be desirable for a system developer if there were an automatic method for creating natural lan- guage generation components that can produce quality output efficiently. We conduct experi- ments that show that this goal appears to be realizable. In particular we discuss a natural language generation system that is composed of SPoT, a trainable sentence planner, and FER- GUS, a stochastic surface realizer. We show how these stochastic NLG components can be made to work together, that they can be ported to new domains with apparent ease, and that such NLG components can be integrated in a real-time dialog system. 1 Introduction Systems that interact with the user via natural language are in their infancy. As these systems mature and become more complex, it would be desirable for a system developer if there were automatic methods for creating natural language generation (NLG) components that can produce quality output efficiently. Stochas- tic methods for NLG may provide such auto- maticity, but most previous work (Knight and Hatzivassiloglou, 1995), (Langkilde and Knight, 1998), (Oh and Rudnicky, 2000), (Uchimoto et al., 2000), (Bangalore and Rambow, 2000) con- centrate on the specifics of individual stochastic methods, ignoring other issues such as integra- bility, portability, and efficiency. In contrast, this paper investigates how different stochastic NLG components can be made to work together effectively, whether they can easily be ported to new domains, and whether they can be inte- grated in a real-time dialog system. Request(DEPART−DATE) Surface Generator FERGUS TTS SPoT Dialog Manager Sentence Planner DM Imp−conf(N) soft−merge Text to Speech Implicit−confirm(NEWARK) Implicit−confirm(DALLAS) period Imp−conf(D) Flying from Newark to Dallas. What date would you like to leave? Request(D−D) Figure 1: Components of an NLG system. Recall the basic tasks in NLG. During text planning, content and structure of the target text are determined to achieve the overall com- municative goal. During sentence planning, lin- guistic means—in particular, lexical and syn- tactic means—are determined to convey smaller pieces of meaning. During realization, the spec- ification chosen in sentence planning is trans- formed into a surface string by linearizing and inflecting words in the sentence (and typically, adding function words). Figure 1 shows how such components cooperate to generate text corresponding to a set of communicative goals. Our work addresses both the sentence plan- ning stage and the realization stage. The sen- tence planning stage is embodied by the SPoT sentence planner (Walker et al., 2001), while the surface realization stage is embodied by the FERGUS surface realizer (Bangalore and Ram- bow, 2000). We extend the work of (Walker et al., 2001) and (Bangalore and Rambow, 2000) in various ways. We show that apparently each of SPoT and FERGUS can be …

Content truncated to 500 words