J. Dowding, R. Moore, F. Andry, D. Moran; Interleaving syntax and semantics in an efficient bottom-up parser; ACL94; pp. 110-116; Las Cruces, New Mexico; 1994.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....are given for L in the learning sample, the information is duplicated to produce one example for each tag. The examples found in DIC and those extracted from TRAIN have been processed exactly in the same way and have the same weight for training. In order to achieve a better WSD, it is important [2, 13] to take the grammatical tags of the words into account. For such a task, we have used our ECSTA tagger [14] Yarowsky [15] highlights various behaviors based on syntactic categories: directly adjacent adjectives or nouns best disambiguate nouns. Our assumption is quite different; we would like ....

J. Dowding, R. Moore, F. Andry, D. Moran; Interleaving syntax and semantics in an efficient bottom-up parser; ACL94; pp. 110-116; Las Cruces, New Mexico; 1994.

....as suggested in (Roussel, 1999) 5. Related works and conclusion Previous works have shown that focusing parsing first on semantics can lead to superior speed efficiency than syntax first approach, particularly on restricted domain as shown in (Lytinen, 1991) but also for large coverage grammar (Dowding et al. 1994). The trees currently developped for our application and their lexicalization are closed from the semantic grammars paradigm (Seneff, 1992) and works on terminological variability (Jacquemin, 1999) We expect that such a LTAG grammar will allow, in our application, a stronger and an easier ....

DOWDING J., MOORE R., ANDRY F. & MORAN D. (1994). Interleaving syntax and semantics in an efficient bottom-up parser. In ACL'94.

....Robert Moore Full name Air Travel Information Service System of SRI Organization SRI International Status Completed Based on CLE, Nuance, Truetalk Used by CommandTalk, ATIS at SRI Home page http: www.ai. sri.com natural language projects arpa sls nat lang.html References [DGA 94] DMAM94] Purpose Spoken natural language parsing and semantic interpretation system. Domain Coverage Gemini has been used in multiple domains. DGA 94] describes tests on the ATIS corpus. The lexicon for this domain has 1,315 base entries. Including morphological variants, the vocabulary consists ....

John Dowding, Robert Moore, Francois Andry, and Douglas Moran. Interleaving syntax and semantics in an efficient bottom-up parser. In Proc. of the 32 nd Annual Meeting of the Association for Computational Linguistics, pages 110--116, Las Cruces, NM, June27--30 1994.

.... can be very useful for disambiguating parses or eliminating impossible sentence hypotheses from a word graph produced by a speech recognizer [110] In addition to lexical features, semantic information is sometimes used by parsers to eliminate sentence hypotheses based on semantic information [84, 116, 117, 118, 132, 137, 138]. In our parser, lexical and semantic features are associated with the category of a word [21, 106, 103, 108, 109, 110, 132] As shown in Figure 3.5, a word in the dictionary has a set of possible values for each lexical feature defined for a possible category of the word. It is possible for a ....

John Dowding, Robert Moore, Francois Andry, and Douglas Moran. Interleaving syntax and semantics in an efficient bottom-up parser. In Proceedings of the 32nd Annual Meeting of the Association for Computational Linguistics, pages 110--116, June 1994.

....sentence is mapped to a CS in context 2. how a CS is mapped to an expression in VOL 3. what the scope of VOL is. 1.3. 1 From Sentences to CS To parse and build an initial semantics for a descriptive sentence, we propose to use the Gemini Natural Language system (Dowding et al. 1993, Alshawi 1992, Dowding et al. 1994) to produce Quasi Logical Forms (QLFs) which are representations of the linguistic meanings of sentences. The QLFs will be pragmatically resolved by abduction, discussed below. Sentence(6) will have a QLF like (7) axis measure(f; m 2 ; w) facial feature(nose; f; F ) m 2 m 1 Here, the noun ....

Dowding, J., R. Moore, F. Andry, and D. Moran. 1994. Interleaving syntax and semantics in an efficient bottom-up parser. In Proceedings of the Thirty-Second Annual Meeting of the ACL, Las Cruces, New Mexico. Association for Computational Linguistics.

.... the constraints can be applied at that level [Mahesh, 1994] the restrictions can be on deep structure syntactic relations [Segond and Jensen, 1992] the lexicon can specify an Elist of constraints for each word [Binot and Ribbens, 1986] or we can have sortal constraints on the logical form [Dowding et al. 1994]. Even Chomsky in his exposition of transformational grammar [1965] allowed for them. 2.2.2 Psycholinguistics Since the 1970 s, psycholinguists have debated what sort of information humans use to process language, and then (of course) how that information is used. For years, two purely syntactic ....

John Dowding, Robert Moore, Fran¸cois Andery, and Douglas Moran, "Interleaving Syntax and Semantics in an Efficient Bottom-Up Parser," In Proceedings of the 32nd Annual Meeting of the Association for Computational Linguistics, pages 110-- 116, 1994.

....based on Nuance, a commercial continuous speech speaker independent speech recognizer developed from SRI technology. Its language model is compiled [5] from the Gemini grammar used by the Natural Language agent. ffl Natural Language based on Gemini [2] performs syntactic and semantic analysis [3] and text generation [7] ffl Contextual Interpretation (CI) This agent is described in detail in section 3. ffl Speech Synthesis based on the Festival speech synthesizer 1 developed by the Centre for Speech Technology Research (CSTR) at the University of Edinburgh. ffl Prosody ....

John Dowding, Robert Moore, Francois Andry, and Douglas Moran. Interleaving Syntax and Semantics in an Efficient Bottom-Up Parser. In Proceedings of the Thirty-Second Annual Meeting of the ACL, Las Cruces, New Mexico, 1994. Association for Computational Linguistics.

....fragments when an utterance cannot be analyzed as a single phrase or utterance, and (3) a new context mechanism for air travel planning that constructs an explicit model of the user s intended itinerary. 1. INTRODUCTION The principal natural language component of SRI s ATIS system is Gemini [1, 2], a unification based natural language processing system. The Gemini system combines a set of general syntactic and semantic rules for English with a domainspecific lexicon and sortal selectional restrictions, to produce sorted logical forms for natural language utterances. The output is derived ....

J. Dowding, R. Moore, F. Andry, and D. Moran, "Interleaving Syntax and Semantics in an Efficient BottomUp Parser," in Proceedings 32nd Annual Meeting of the Association for Computational Linguistics, New Mexico State University, Las Cruces, New Mexico, 27 June -- 1 July 1994, pp. 110--116.

....that can be parsed in sync; that is, it guarantees that every word string that can be parsed by the natural language component is a potential recognition hypothesis, and vice versa. 2. 2 Natural Language The natural language (NL) agent consists of a thin agent layer on top of SRI s Gemini (Dowding et al. 1993, 1994), a natural language parsing and semantic interpretation system based on unification grammar. Unification grammar means that grammatical categories incorporate features that can be assigned values; so that when 4 grammatical category expressions are matched in the course of parsing or semantic ....

Dowding, J., R. Moore, F. Andry, and D. Moran (1994) "Interleaving Syntax and Semantics in an Efficient Bottom-Up Parser," in Proceedings 32nd Annual Meeting of the Association for Computational Linguistics, Las Cruces, New Mexico, pp. 110--116.

....approximately 23,000 utterances of ATIS spontaneous speech data. 4. NATURAL LANGUAGE UNDERSTANDING The natural language understanding component accepts word hypotheses from the recognizer, and produces two outputs, the simplified logical form (SLF) and the answer to the query. The Gemini system [3, 4] has been incorporated into this application without significant modification. Gemini uses a word synchronous bottom up parser to process speaker utterances. An implication of this approach is that it is possible to start syntactic and semantic processing of the utterance before the entire ....

J. Dowding, R. Moore, F. Andry, and D. Moran, "Interleaving Syntax and Semantics in an Efficient BottomUp Parser," in Proceedings 32nd Annual Meeting of the Association for Computational Linguistics, New Mexico State University, Las Cruces, New Mexico (27 June -- 1 July 1994).

....single grammar using Gemini (Dowding et al. 1993) a unification based grammar formalism. This grammar is used to provide all the language modeling capabilities of the system, including the language model used in the speech recognizer, the syntactic and semantic interpretation of user utterances (Dowding et al. 1994), and the generation of system responses (Shieber et al. 1990) For speech recognition, Gemini uses the Nuance speech recognizer. Nuance accepts language models written in a Grammar Specification Language (GSL) format that allows context free, as well as the more commonly used finite state, ....

J. Dowding, R. Moore, F. Andry, and D. Moran. 1994. Interleaving Syntax and Semantics in an Efficient Bottom-Up Parser. In Proceedings of the Thirty-Second Annual Meeting of the ACL, Las Cruces, New Mexico. Association for Computational Linguistics.

....even the termination, of the processing strategy) The following example shows a rule written in the unification based formalism used in the Core Language Engine (Alshawi, 1992) developed by SRI International s research group in Cambridge, England. This formalism is also used in the Gemini system (Dowding et al. 1993, 1994) developed by SRI in Menlo Park, California: S: tensed=yes] NP: person=P,num=N] VP: tensed=yes,person=P,num=N] What unification grammar adds to context free grammar is the notion of feature constraints. In the notation presented here, grammatical categories are specified in terms of a major ....

Dowding, J., R. Moore, F. Andry, and D. Moran (1994) "Interleaving Syntax and Semantics in an Efficient Bottom-Up Parser," in Proceedings of the 32nd Annual Meeting of the Association for Computational Linguistics, Las Cruces, New Mexico, pp. 110--116.

....it provides simple mix and match for the components. In developing systems, we have used three different natural language (NL) systems: a simple one, based on Prolog DCG (Definite Clause Grammar) then an intermediate one, based on CHAT [16] and finally, our most capable research system GEMINI [6, 7]. The ability to trivially substitute one natural language agent for another has been very useful in rapid prototyping of systems. The DCG based agent is used during the early stages of development because grammars are easily written and modified. Writing grammars for the more sophisticated NL ....

....the utility of the concept, a more extensive analysis was conducted of the task and the commands used, and more capable prototypes were developed. One of the significant enhancements was the replacement of our simplest natural language agent (DCG based) with our most sophisticated (based on GEMINI [6, 7]) Summarization of Conversation A system that summarizes conversations provided a novel opportunity to use two instances of a speech recognition agent, in conjunction with a single instance of a text processing agent ( 10] In this system, MIMI, two Japanese speakers engage in a conversation, ....

John Dowding, Robert Moore, Francois Andry, and Doug las Moran. Interleaving syntax and semantics in an efficient bottom-up parser. In Proc. of the 32nd Annual Meeting of the Association for Computational Linguistics, pages 110--116, New Mexico State University, Las Cruces, New Mexico, 27 June -- 1 July 1994.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC