Abstract We investigate the problem of improving performance in distributional word similarity systems trained on sparse data, focusing on a family of similarity functions we call Dice-family functions (Dice 1945Ecology26(3): 297–302), including the similarity function introduced in Lin (1998Proceedings of the 15th International Conference on Machine Learning, 296–304), and Curran (2004 PhD thesis, University of Edinburgh. College of Science and Engineering. School of Informatics), as well as a generalized version of Dice Coefficient used in data mining applications (Strehl 2000, 55). We propose a generalization of the Dice-family functions which uses a weight parameter α to make the similarity functions asymmetric. We show that this generalized family of functions (α systems) all belong to the class of asymmetric models first proposed in Tversky (1977Psychological Review84: 327–352), and in a multi-task evaluation of ten word similarity systems, we show that α systems have the best performance across word ranks. In particular, we show that α-parameterization substantially improves the correlations of all Dice-family functions with human judgements on three words sets, including the Miller–Charles/Rubenstein Goodenough word set (Miller and Charles 1991Language and Cognitive Processes6(1): 1–28; Rubenstein and Goodenough 1965Communications of the ACM8: 627–633).

Current alternatives for language modeling are statistical techniques based on large amounts of training data, and hand-crafted context-free or finite-state grammars that are difficult to build and maintain. One way to address the problems of the grammar-based approach is to compile recognition grammars from grammars written in a more expressive formalism. While theoretically straight-forward, the compilation process can exceed memory and time bounds, and might not always result in accurate and efficient speech recognition. We will describe and evaluate two approaches to this compilation problem. We will also describe and evaluate additional techniques to reduce the structural ambiguity of the language model.

CommandTalk (Moore et al., 1997) is a spokenlanguage interface to the ModSAF battle eld simulator that allows simulation operators to generate and execute military exercises by creating

Article Free Access Share on Gemini: a natural language system for spoken-language understanding Authors: John Dowding SRI International, Menlo Park, CA SRI International, Menlo Park, CAView Profile , Jean Mark Gawron SRI International, Menlo Park, CA SRI International, Menlo Park, CAView Profile , Doug Appelt SRI International, Menlo Park, CA SRI International, Menlo Park, CAView Profile , John Bear SRI International, Menlo Park, CA SRI International, Menlo Park, CAView Profile , Lynn Cherny SRI International, Menlo Park, CA SRI International, Menlo Park, CAView Profile , Robert Moore SRI International, Menlo Park, CA SRI International, Menlo Park, CAView Profile , Douglas Moran SRI International, Menlo Park, CA SRI International, Menlo Park, CAView Profile Authors Info & Claims ACL '93: Proceedings of the 31st annual meeting on Association for Computational LinguisticsJune 1993Pages 54–61https://doi.org/10.3115/981574.981582Published:22 June 1993Publication History 43citation1,076DownloadsMetricsTotal Citations43Total Downloads1,076Last 12 Months25Last 6 weeks7 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Publisher SiteeReaderPDF

We propose a semantics for locative expressions such as near Jones or west of Denver, an important subsystem for NLP applications. Locative expressions denote regions of space, and serve as arguments to predicates, locating objects and events spatially. Since simple locatives occupy argument positions, they do NOT participate in scope ambiguities---pace one common view, which sees locatives as logical operators. Our proposal justifies common representational practice in computational linguistics, accounting for how locative expressions function anaphorically, and explaining a wide range of inference involving locatives. We further demonstrate how the argument analysis may accommodate multiple locative arguments in a single predicate. The analysis is implemented for use in a database query application.

This paper describes a natural language processing system implemented at Hewlett-Packard's Computer Research Center. The system's main components are: a Generalized Phrase Structure Grammar (GPSG); a top-down parser; a logic transducer that outputs a first-order logical representation; and a "disambiguator" that uses sortal information to convert "normal-form" first-order logical expressions into the query language for HIRE, a relational database hosted in the SPHERE system. We argue that theoretical developments in GPSG syntax and in Montague semantics have specific advantages to bring to this domain of computational linguistics. The syntax and semantics of the system are totally domain-independent, and thus, in principle, highly portable. We discuss the prospects for extending domain-independence to the lexical semantics as well, and thus to the logical semantic representations.