Insights into the Dialogue Processing of VERBMOBIL

We present the dialogue module of the speech-to-speech translation system VERBMOBIL. We follow the approach that the solution to dialogue processing in a mediating scenario can not depend on a single constrained processing tool, but on a combination of several simple, efficient, and robust components. We show how our solution to dialogue processing works when applied to real data, and give some examples where our module contributes to the correct translation from German to English. 1 I n t r o d u c t i o n The imPlemented research prototype of the speechto-speech translation system VEaBMOBIL (Wahlster, 1993; Bub and Schwinn, 1996) consists of more than 40 modules for both speech and linguistic processing. The central storage for dialogue information within the overall system is the dialogue module that exchanges data with 15 of the other modules. Basic notions within VERBMOBIL are t u ~ 8 a n d u t t e r a n c e s . A turn is defined as one contribution of a dialogue participant. Each turn divides into utterances that sometimes resemble clauses as defined in a traditional grammar. However, since we deal exclusively with spoken, unconstrained contributions, utterances are sometimes just pieces of linguistic material. For the dialogue module, the most important dialogue related information extracted for each utterance is the so called dialogue act (Jekat et al., 1995). Some dialogue acts describe solely the illocutionary force, while other more domain specific ones describe additionally aspects of the propositional content of an utterance. Prior to the selection of the dialogue acts, we analyzed dialogues from VERBMOBIL'S corpus of spoken and transliterated scheduling dialogues. More than 500 of them have been annotated with dialogue related information and serve as the empirical foundation of our work. Throughout this paper we will refer to the example dialogue partly shown in figure 1. The translations are as the deep processing line of VERBMOBIL provides them. We also annotated the utterances with the dialogue acts as determined by the semantic evaluation module. ' ' / / ' ' shows where utterance boundaries were determined. We start with a brief introduction to dialogue processing in the VERBMOBIL setting. Section 3 introduces the basic data structures followed by two sections describing some of the tasks which are carried out within the dialogue module. Before the concluding remarks in section 8, we discuss aspects of robustness and compare our approach to other systems. 2 I n t r o d u c t i o n t o D i a l o g u e P r o c e s s i n g i n VERBMOBIL In contrast to many other NL-systems, the VEaBMOBIL system is mediating a dialogue between two persons. No restrictions are put on the locutors, except for the limitation to stick to the approx. 2500 words VERBMOBIL recognizes. Therefore, VERBMOBIL and especially its dialogue component has to follow the dialogue in any direction. In addition, the dialogue module is faced with incomplete and incorrect input, and sometimes even gaps. When designing a component for such a scenario, we have chosen not to use one big constrained processing tool. Instead, we have selected a combination of several simple and efficient approaches, which together form a robust and efficient processing platform. As an effect of the mediating scenario, our module cannot serve as a "dialogue controller" like in man-machine dialogues. The only exception is when