Articles

This paper reports results obtained in benchmark tests conducted within the ARPA Spoken Language program in November and December of 1993. In addition to ARPA contractors, participants included a number of %olunteers", including foreign participants from Canada, France, Germany, and the United Kingdom. The body of the paper is limited …...

This paper describes eight telephone-speech corpora at vari- ous stages of development at the Center for Spoken Language Understanding. For each corpus, we describe data collection procedures, methods of soliciting callers, protocol used to col- lect the data, transcriptions that accompany the speech data, and the expected release date. The …...

In this paper, we introduce the new paradigm used in the most re- cent ARPA-sponsored Continuous Speech Recognition (CSR) eval- uation and then discuss the important features of the test design. The 1993 CSR evaluation was organized in a novel fashion in an attempt to accomodate research over a broad …...

Information about words--their pronunciation, syntax and meaning--is a crucial and costly part of human language technology. Many questions remain about the best way to express and use such lexical information. Nevertheless, much of this information is common to all current approaches, and therefore the effort to collect it can usefully …...

Two themes have evolved in speech and text image processing work at Xerox PARC that expand and redefine the role of recognition tech- nology in d~ument-oriented appficafions. One is the development of systems that provide functionality similar to that of text proces- sors but operate directly on audio and scanned …...

Basic research is critically needed to guide the development of a new generation of multimodal and multilingual NL sys- tems. This paper summarizes the goals, capabilities, com- puting environment, and performance characteristics of a new semi-automatic simulation technique. This technique has been designed to support a wide spectrum of empiri- …...

This paper describes some recent experiments that assess user behavior in a multi-modal environment in which actions can be performed with equivalent effect in speech, keyboard or scroller modes. Results indicate that users freely choose speech over other modalities, even when it is less efficient in objective terms, such as …...

Natural language experiments in information retrieval have often been inconclusive due to the lack of large text bases with associated queries and relevance judgments. This pa- per describes experiments in incremental query processing and indexing with the INQUERY information retrieval sys- tem on the TIPSTER queries and document collection. The …...

The importance of good weighting methods in information retrieval -- methods that stress the most useful features of a document or query representative -- is examined. Evidence is presented that good weighting methods are more important than the feature selection process and it is suggested that the two need to …...

This paper addresses two main questions: (a) Can listeners as- sign values of perceived boundary strength to the juncture between any two words? (b) If so, what is the relationship between these values and various (combinations of) suprasegmental features. Three speakers read a set of twenty utterances of varying length …...

Prosodic patterns provide important cues for resolving syn- tactic ambiguity, and might he used to improve the accu- racy of automatic speech understanding. With this goal, we propose a method of scoring syntactic parses in terms of ob- served prosodic cues, which can be used in ranking sentence hypotheses and …...

Interpreting fttUy natural speech is an important goal for spoken language understanding systems. However, while corpus studies have shown that about 10% of spontaneous utterances contain self- corrections, or REPAIRS, little is known about the extent to which cues in the speech signal may facilitate repair processing. We identify several …...

In natural speech, durations of phonetic segments are strongly de- pendent on contextual factors. Quantitative descriptions of these contextual effects have appfications in text-to-speech synthesis and in automatic speech recognition. In this paper, we describe a speaker- dependent system for predicting segmental duration from text, with emphasis on the statistical …...

This work assesses the contribution of domain-specific prosodic modelling to synthetic speech quality in a name-and-address information service. A prosodic processor analyzes the textual structure of labelled input strings, and inserts markers which spec- ify the intended prosody for the DECtalk text-to-speech synthe- sizer. These markers impose discourse-level prosodic organization, …...

This paper provides a brief...

A semantic concordance is a textual corpus and a lexicon So com- bined that every substantive word in the text is linked to its appropriate ~nse in the lexicon. Thus it can be viewed either as a corpus in which words have been tagged syntactically and semanti- cally, or as …...

In this paper we propose to define selectional preference and se- mantic similarity as information-theoretic relationships involving conceptual classes, and we demonstrate the applicability of these definitions to the resolution of syntactic ambiguity. The space of classes is defined using WordNet [8], and conceptual relationships are determined by means of …...

Our work focuses on identifying various types of lexical data in large corpora through statistical analysis. In this paper, we present a method for grouping adjectives according to their mean- ing, as a step towards the automatic identification of adjectival scales. We describe how our system exploits two sources of …...

Previous work [Gale, Church and Yarowsky, 1992] showed that with high probability a polysemous word has one sense per discourse. In this paper we show that for certain definitions of collocation, a polysemous word exhibits essentially only one sense per collocation. We test this empirical hypothesis for several definitions of …...

The three corpus-based statistical sense resolution methods studied here attempt to infer the correct sense of a polyse- mous word by using knowledge about patterns of word co- occurrences. The techniques were based on Bayesian decision theory, neural networks, and content vectors as used in in- formation retrieval. To understand …...