Abstract not found

A lot of work remains to be done in the domain of a better integration of speech recognition and language processing systems. This paper gives an overview of several strategies for integrating linguistic models into speech understanding systems and investigates several ways of producing sets of hypotheses that include more "semantic" variability than usual language models. The main goal is to present and demonstrate by actual experiments that sequential coupling may be efficiently achieved by word-lattice syntactic analyzers, efficiently parsing the huge number of hypothesis (i.e. possible sentences) contained in the lattice produced by the speech recognizer. 1. Motivations The past decade has seen significant progress in speech recognition technology: word (recognition) error rates continue to drop by a factor of 2 every two years (Rabiner et al., 1996) and high performance systems are now becoming available. Several factors have contributed to this rapid progress: ffl Generalisati...

This article presents a dependency parsing scheme using an extended finite-state approach. The parser augments input representation with “channels ” so that links representing syntactic dependency relations among words can be accommodated and iterates on the input a number of times to arrive at a fixed point. Intermediate configurations violating various constraints of projective dependency representations such as no crossing links and no independent items except sentential head are filtered via finite-state filters. We have applied the parser to dependency parsing of Turkish. 1.

This paper describes methods for approximating context-free grammars with finite state machines. Unlike the method derived from the LR(k) parsing algorithm described in Pereira and Wright (1991), these methods use grammar transformations based on the left-corner grammar transform (Rosenkrantz and Lewis II, 1970; Aho and Ullman, 1972). One advantage of the left corner methods is that they generalize straightforwardly to complex feature "unification based" grammars, unlike the LR(k) based approach. Left-corner based techniques are natural for this kind of application because (with a simple optimization) they can parse pure left-branching or pure rightbranching structures with a stack depth of one (two if terminals are pushed and popped from the stack). Higher stack depth occurs with center-embedded structures, which humans find difficult to comprehend. This suggests that we may get a finite-state approximation to human performance by simply imposing a stack depth bound, and ignoring any parses which require stack depths greater than this bound. We provide a simple tree-geometric description of the configurations that cause an increase in a left corner parser's stack depth below. We also take this opportunity to point out some simple extensions of this technique, which can capture using pure grammar transform techniques a range of parsing strategies similiar to the generalized left-corner parsing strategies (Demers, 1977; Nijholt, 1980). Finally, this paper discusses methods for using these finite state approximations in actual parsing applications, showing how the finite state machine can be used as an oracle to guide a left corner parser (and hence recover the tree structure) and how to construct a transducer that produces partial brackettings.

Abstract not found