Articles

A plan is presented for evaluating natural language processing (NLP) systems that have focused on the issues of text understanding as exemplified in short texts from military messages. The plan includes definition of bodies of text to use as development and test data, namely the narrative lines from one type …...

Recently, we initiated a project to develop a phonetically-based spoken language understanding system called SUMMIT. In contrast to many of the past efforts that make use of heuristic rules whose development requires intense knowledge engineering, our approach attempts to express the speech knowledge within a formal framework using well-defined mathematical …...

A new natural language system, TINA, has been developed for applications involving speech understanding tasks, which integrates key ideas from context free grammars, Augmented Transition Networks (ATN's) [1], and Lexical Functional Grammars (LFG's) [2]. The parser uses a best-first search strategy, with probability assignments on all arcs obtained automatically from …...

The Lincoln stress-resistant HMM CSR has been extended to large vocabulary continuous speech for both speaker-dependent (SD) and speaker-independent (SI) tasks. Performance on the DARPA Resource Manage- ment task (991 word vocabulary, perplexity 60 word-pair grammar) [1] is 3.4% word error rate for SD training of word-context-dependent triphone models and …...

The Penman text generation system has been used within several different experimental application domains, demonstrating that it provides the basis for an adaptable general purpose text generation capability. Linking with these applications also indicated several ways that Penman's interface with applications could be improved. Penman's interface with applications is described, …...

This paper reports on a study of recognition performance for a group of new users during their first month of experience with the TANGORA system. TANGORA is a 20,000 word, speaker dependent, isolated-word system which transcribes speech input into text in real-time. Twelve users, six males and six females, participated …...

When speech understanding systems are used in real applications, they will have to deal with phenomena peculiar to spontaneous speech. People use language differently when they speak than when they write. Spoken language contains many interjections, filled pauses, etc. Speakers often don't use well-formed sentences. They speak in phrases, have …...

This paper describes recent improvements in the SPHINX Speech Recognition System. These enhancements include function-phrase modeling, between-word coarticulation modeling, and corrective training. On the DARPA resource management task, SPHINX attained a speaker-independent word accuracy of 96% with a grammar (perplexity 60), and 82% without grammar (perplexity 997). 1....

This paper presents some issues that arise in building voice- driven interfaces to complex applications and describes some of the approaches that we have developed for this purpose. To test these approaches, we have implemented a voice spreadsheet and have begun observation of users interacting with it....

Although natural language technology has achieved a high degree of domain independence through separating domain-independent modules from domain-dependent knowledge bases, portability, as measured by effort to move from one application to another, is still a problem. Here we describe a knowledge acquisition tool (KNACQ) that has sharply decreased our effort …...

We describe HARC, a system for speech understand- ing that integrates speech recognition techniques with natural language processing. The integrated system uses statistical pattern recognition to build a lattice of potential words in the input speech. This word lattice is passed to a unification parser to derive all possible associated …...

The BBN BYBLOS continuous speech recognition system has been used to develop a method of speaker adaptation from limited training. The key step in the method is the estimation of a probabilistic spectral mapping between a prototype speaker, for whom there exists a well-trained speaker-dependent hidden Markov model (HMM), and …...

In this paper we describe the algorithms used in the BBN BYBLOS Continuous Speech Recognition system. The BYBLOS system uses context-dependent hidden Markov models of phonemes to provide a robust model of phonetic coarticulation. We provide an update of the ongoing research aimed at improving the recognition accuracy. In the …...

Developing knowledge bases for AI systems takes too long and costs too much. Even a "portable" system may be expensive to use because its installation takes a long time or requires the labor of scarce, highly-trained people. BBN has recently created a tool for acquisition which dramatically reduces the time …...

Speaker independent phonetic Iranscription of fluent speech is performed using an ergodic continuously variable duration hidden Markov model (CVDHMM) to represent the acoustic, phonetic and phonotactic structure of speech. An important property of the model is that each of its fifty-one states is uniquely identified with a single phonetic unit. …...

In this paper we describe a framework for research into translation that draws on a combination of two existing and independently constructed technologies: an analysis component developed for German by the EUROTRA-D (ET-D) group of IAI and the genera- tion component developed for English by the Penman group at ISI. …...

We sketch and illustrate an approach to machine translation that exploits the potential of simultaneous correspondences between separate levels of linguistic representation, as formalized in the LFG notion of codescriptions. The approach is illustrated with examples from English, German and French where the source and the target language sentence show …...

A framework for translating speaker's meaning or intention is proposed based on two notions, Illocutionary Force Types (IFTs) for analysis and Decision Parameters (DPs) for generation. IFTs are a certain kind of classification of utterances concerning speaker's meaning. DPs present background information of language use in order to derive an …...

This paper presents an algorithm for incremental chart parsing, outlines how this could be embed- ded in an interactive parsing system, and discusses why this might be useful. Incremental parsing here means that input i8 analysed in a piecemeal fash- ion, in particular allowing arbitrary changes of previ- ous input …...

We present an algorithm for the generation of sentences from the semantic representations of Unification Categorial Grammar. We discuss a variant of Shieber's semantic monotonicity requirement and its utility in our algorithm. We indicate how the algorithm may be extended to other grammars obeying the same requirement. Appendices contain a …...