This paper presents the XTAG system, a grammar development tool based on the Tree Actioining Grammar (IG) formalism that includes a wide-coverage syntactic grammar' or English. The various components of the system are discussed and preliminary evaluation results fi'om the parsing of various corpora are given. Results from the comparison of XTAG agaiust the IBM statistical parser' and the Alvey Natural Language Tool parser are also given.

In this paper a new, tree-trellis based fast search for finding the N best sentence hypotheses in continuous speech recognition is proposed. The search consists of two parts: a forward, time-synchronous, trellis search and a backward, time asynchronous, tree search. In the first module the well known Viterbi algorithm is used for finding the best hypothesis and for preparing a map of all partial paths scores time synchronously. In the second module a tree search is used to grow partial paths backward and time asynchronously. Each partial path in the backward tree search is rank ordered in a stack by the corresponding full path score, which is computed by adding the partial path score with the best possible score of the remaining path obtained from the trellis path map. In each path growing cycle, the current best partial path, which is at the top of the stack, is extended by one arc (word). The new tree-trellis search is different from the traditional time synchronous Viterbi search in its ability for finding not just the best but the N-best paths of different word content. The new search is also different from the A * algorithm, or the stack algorithm, in its capability for providing an exact, full path score estimate of any given partial (i.e., incomplete) path before its completion. When compared with the best candidate Viterbi search, the search complexities for finding the N-best strings are rather low, i.e., only a fraction more computation is needed.

Most large vocabulary speech recognition systems essentially consist of a training algorithm and a recognition structure which is essentially a search for the best path through a rather large decoding network. Although the performance of the recognizer is crucially tied to the details of the training procedure, it is absolutely essential that the recognition structure be efficient in terms of computation and memory, and accurate in terms of actually determining the best path through the lattice, so that a wide range of training (sub-word unit creation) strategies can be efficiently evaluated in a reasonable time period. We have considered an architecture in which we incorporate several well known procedures (beam search, compiled network, etc.) with some new ideas (stacks of active network nodes, likelihood computation on demand, guided search, etc.) to implement a search procedure which maintains the accuracy of the full search but which can decode a single sentence in about one minute of computing time (about 20 times real time) on a vectorized, concurrent processor. The ways in which we have realized this significant computational reduction are described in this paper.

In this paper we report on the recent advancements and current status of the XTAG Project# housed at the University of Pennsylvania. We discuss the current cov# erage of the system# as evaluated on the TSNLP English sentences# hierarchical or# ganization of the grammar# and the new and more portable implementation of the X#interface to the grammar and all of the supporting tools in CLISP# which is freely available. We also present a methodology for specializing our grammar to a particu# lar domain# and give some results on this e#ort. 1 Development and Current Status of XTAG 1.1 History of XTAG The XTAG project has been ongoing at Penn in some form or another since 1988. It began with a toy grammar run on LISP machines# and currently has a large English grammar# small grammars in several other languages# a sophisticated X#windows based grammar development environment and nu# merous satellite tools. Approximately 35 people have worked extensively on the system# and at l...

This paper presents the XTAG system, a grammar development tool based on the Tree Adjoining Grammar (TAG) formalism that includes a wide-coverage syntactic grammar for English. The various components of the system are discussed and preliminary evaluation results from the parsing of various corpora are given. Results from the comparison of XTAG against the IBM statistical parser and the Alvey Natural Language Tool parser are also given. 1