Showing papers by "Dan Jurafsky published in 1994"

The berkeley restaurant project.

Abstract: This paper describes the architecture and performance of the Berkeley Restaurant Project (BeRP), a medium-vocabulary, speaker-independent, spontaneous continuous speech understanding system currently under development at ICSI. BeRP serves as a testbed for a number of our speech-related research projects, including robust feature extraction, connectionist phonetic likelihood estimation, automatic induction of multiplepronunciation lexicons, foreign accent detection and modeling, advanced language models, and lip-reading. In addition, it has proved quite usable in its function as a database frontend, even though many of our subjects are non-native speakers of English.

Type underspecification and On-line Type Construction in the Lexicon

Abstract: Many recent lexical and syntactic theories have used TYPE HIERARCHIES to model linguistic generalizations, including valence alternations, morphological generalizations, subregularities, and positive exceptions (Bobrow & Webber 1980; Flickinger et al. 1985; Hudson 1984; Lakoff 1987; Pollard & Sag 1987; Jurafsky 1992; Briscoe et al. 1994; Pollard & Sag 1994). Despite these successes, current type hierarchies are unable to model LEXICAL PRODUCTIVITY: the kind of productive patterns which occur in morphologically recursive languages, lexical borrowing and learning, and productive valence alternations (Hankamer 1989; Pinker 1989). This failure is due to the traditional conception of lexical types as generalizations over actual fully specified entries, functioning like redundancy rules. A lexical type hierarchy gives us an inventory of the word classes in a language, but does not tell us how to use productive processes like inflection to create new forms. To model lexical productivity, we propose to underspecify the type hierarchy. For example, rather than store a type for each surface form of each word of the language, we store a single type for each root and each productive morphological template. Then these types are combined on-line to build types for surface forms in processing or producing an utterance, by an algorithm we call ON-LINE TYPE CREATION. Thus some of the burden typically borne by the lexical type hierarchy is shifted to the processing component, which combines these types on-line. Although our system is embedded in the specific framework of CONSTRUCTION GRAMMAR (Fillmore et al. 1988; Kay 1990; Lakoff 1987; Goldberg 1991; Goldberg 1992; Koenig 1993), it is directly applicable to any typed theory such as HPSG. In fact, we show that on-line type construction can advantageously replace mechanisms like lexical rules which are used in HPSG to model lexical productivity.