Unification-based theories of grammar allow to integrate different levels of linguistic descriptions in the coinmen framework of typed feature structures. Dependencies among the levels are expressed by corefcrences. Though highly attractive theoretically, using such codcscriptions for analysis creates problems of efficiency. We present an approach to a nodular use of codescriptiens on the syntactic and semantic level. Grammatical analysis is performed by tightly coupled parsers running in tandem, each using only designated parts of the grammat- ical description. in the paper we describe the partitioning of grammatical information for the parsers and present results about the performance.

. This article describes a probabilistic context free grammar approximation method for unification grammars. In order to produce good results, the method is combined with an N best parsing extension to chart parsing. The first part of the paper introduces the grammar approximation method, while the second part describes details of an efficient N-best packing and unpacking scheme for chart parsing. 1 Introduction Recently much attention has been payed to the integration of speech and language technology 1 . The concentration on spontaneous speech understanding led to the definition of a robust interface known as the word graph or word lattice between recognition and understanding. Depending on the application, systems are built to provide a shallow stochastic analysis or a deep linguistic analysis of the word lattice. Using a shallow stochastic approach, a rough template-based analysis can be achieved which makes sense in those cases where a fine grained reconstruction of meanings is...

The analysis of spoken dialogs requires the analysis of complete multisentence turns. Especially, the segmentation of turns in sentential or phrasal segments is a problem. In this paper we present a system for turn analysis. It is based on an extension of HPSG grammar for turns and takes into account extra-linguistic prosodic information. We show how this information can be integrated and represented in the grammar, and how it is used to reduce the search space in parsing.

We investigated the performance efficacy of beam search parsing and deep parsing techniques in probabilistic HPSG parsing using the Penn treebank. We first tested the beam thresholding and iterative parsing developed for PCFG parsing with an HPSG. Next, we tested three techniques originally developed for deep parsing: quick check, large constituent inhibition, and hybrid parsing with a CFG chunk parser. The contributions of the large constituent inhibition and global thresholding were not significant, while the quick check and chunk parser greatly contributed to total parsing performance. The precision, recall and average parsing time for the Penn treebank (Section 23) were 87.85%, 86.85%, and 360 ms, respectively. 1

Humans understand spoken language in a continuous manner, incorporating complex semantic and contextual constraints at all levels of language processing on a word-by-word basis, but the standard paradigm for computational processing of language remains sentence-at-a-time, and does not demonstrate the tight integration of interpretations at various levels of processing that humans do. We introduce the fruit carts task domain, which has been specifically designed to elicit language that requires this sort of continuous understanding. A system architecture that incrementally incorporates feedback from a real-world reference resolution module into the parser is presented as a major step towards a continuous understanding system. A preliminary proof in principle shows that real-world knowledge can help resolve certain parsing ambiguities, thus improving accuracy, and that the efficiency of the parser, as measured by the number of constituents built, improves by upwards of 30 % on certain example sentences with multiple attachment ambiguities. A 26 % efficiency improvement was achieved for a dialogue transcript taken from those collected for the fruit carts task domain. We also argue that real-world reference information can help resolve ambiguities in speech recognition. Continuous Understanding of Spoken Language There are a number of speech-to-intention dialogue systems which undertake the task of understanding and/or interperting spoken language, such as Verbmobil (Kasper et al. 1996;

We present a simple approximation method for turning a Head-Driven Phrase Structure Grammar into a context-free grammar. The approximation method can be seen as the construction of the least fixpoint of a certain monotonic function. We discuss an experiment with a large HPSG for Japanese.

this article could not have been written. References

This report presents some word recognition results on the speech-to-speech translation system INTARC 2.0. Our research goal was to build a system with a cognitive oriented architecture. The main topics are incremental, timesynchronous and interactive processing. All modules work on the same time segment processing the signal from left to right. Analyses -- even partial ones -- are passed as soon as possible. Figure 1 shows the overall structure of the system. Details of the architecture of parts of INTARC 2.0 can be found in [1]...

We present a general architecture for incremental interaction between modules in a speech-tointention continuous understanding dialogue system. This architecture is then instantiated in the form of an incremental parser which receives suitability feedback on NP constituents from a reference resolution module. Oracle results indicate that perfect NP suitability judgments can provide a labelled-bracket error reduction of as much as 42% and an efficiency improvement of 30%. Preliminary experiments in which the parser incorporates feedback judgments based on the set of referents found in the discourse context achieve a maximum error reduction of 9.3% and efficiency gain of 4.6%. The parser is also able to incrementally instantiate the semantics of underspecified pronouns based on matches from the discourse context. These results suggest that the architecture holds promise as a platform for incremental parsing supporting continuous understanding.