James Pustejovsky

Last updated

James Pustejovsky (born 1956) [1] is an American computer scientist. He is the TJX Feldberg professor of computer science at Brandeis University in Waltham, Massachusetts, United States. His expertise includes theoretical and computational modeling of language, specifically: Computational linguistics, Lexical semantics, Knowledge representation, temporal and spatial reasoning and Extraction. His main topics of research are Natural language processing generally, and in particular, the computational analysis of linguistic meaning. He holds a B.S. from MIT as well as a PhD from the University of Massachusetts, Amherst.

Contents

Pustejovsky first proposed generative lexicon theory in lexical semantics in an article published in 1991, [2] which was further developed in his 1995 book of the same name. His other interests include temporal reasoning, event semantics, spatial language, language annotation, computational linguistics, and machine learning.

Current research

Pustejovsky's research group's current projects include the TimeML and ISO-Space projects. The TimeML project is a standard markup language for temporal events in a document, and has recently been adopted as ISO-TImeML by the ISO. ISO-Space is an ISO-directed effort to create an expressive specification for the representation of spatial information in language. His previous work included the Medstract project, an effort to extract information from medical documents using current natural language processing technology.

Related Research Articles

Semantics is the study of reference, meaning, or truth. The term can be used to refer to subfields of several distinct disciplines, including philosophy, linguistics and computer science.

Natural-language understanding (NLU) or natural-language interpretation (NLI) is a subtopic of natural-language processing in artificial intelligence that deals with machine reading comprehension. Natural-language understanding is considered an AI-hard problem.

Lexical semantics, as a subfield of linguistic semantics, is the study of word meanings. It includes the study of how words structure their meaning, how they act in grammar and compositionality, and the relationships between the distinct senses and uses of a word.

<span class="mw-page-title-main">Ray Jackendoff</span> American linguist and philosophy professor

Ray Jackendoff is an American linguist. He is professor of philosophy, Seth Merrin Chair in the Humanities and, with Daniel Dennett, co-director of the Center for Cognitive Studies at Tufts University. He has always straddled the boundary between generative linguistics and cognitive linguistics, committed to both the existence of an innate universal grammar and to giving an account of language that is consistent with the current understanding of the human mind and cognition.

In semantics, mathematical logic and related disciplines, the principle of compositionality is the principle that the meaning of a complex expression is determined by the meanings of its constituent expressions and the rules used to combine them. This principle is also called Frege's principle, because Gottlob Frege is widely credited for the first modern formulation of it. The principle was never explicitly stated by Frege, and it was arguably already assumed by George Boole decades before Frege's work.

In linguistics, coercion is a term applied to a process of reinterpretation triggered by a mismatch between the semantic properties of a selector and the semantic properties of the selected element. As Catalina Ramírez explains it, this phenomenon is called coercion because the process forces meaning into a lexical phrase where there is otherwise a discrepancy of the semantic aspects of the phrase. The term was first used in the semantic literature in 1988 by Marc Moens and Mark Steedman, who adopted it due to its "loose analogy with type-coercion in programming languages.” In his written framework of the generative lexicon, Pustejovsky (1995:111) defines coercion as "a semantic operation that converts an argument to the type which is expected by a function, where it would otherwise result in a type error."

<span class="mw-page-title-main">Charles J. Fillmore</span> American linguist

Charles J. Fillmore was an American linguist and Professor of Linguistics at the University of California, Berkeley. He received his Ph.D. in Linguistics from the University of Michigan in 1961. Fillmore spent ten years at Ohio State University and a year as a Fellow at the Center for Advanced Study in the Behavioral Sciences at Stanford University before joining Berkeley's Department of Linguistics in 1971. Fillmore was extremely influential in the areas of syntax and lexical semantics.

In linguistics, linguistic competence is the system of unconscious knowledge that one knows when they know a language. It is distinguished from linguistic performance, which includes all other factors that allow one to use one's language in practice.

Angelika Kratzer is a professor emerita of linguistics in the department of linguistics at the University of Massachusetts Amherst.

Eugene Charniak is a professor of computer Science and cognitive Science at Brown University. He holds an A.B. in Physics from the University of Chicago and a Ph.D. from M.I.T. in Computer Science. His research has always been in the area of language understanding or technologies which relate to it, such as knowledge representation, reasoning under uncertainty, and learning. Since the early 1990s he has been interested in statistical techniques for language understanding. His research in this area has included work in the subareas of part-of-speech tagging, probabilistic context-free grammar induction, and, more recently, syntactic disambiguation through word statistics, efficient syntactic parsing, and lexical resource acquisition through statistical means.

Generative lexicon (GL) is a theory of linguistic semantics which focuses on the distributed nature of compositionality in natural language. The first major work outlining the framework is James Pustejovsky's 1991 article "The Generative Lexicon". Subsequent important developments are presented in Pustejovsky and Boguraev (1993), Bouillon (1997), and Busa (1996). The first unified treatment of GL was given in Pustejovsky (1995). Unlike purely verb-based approaches to compositionality, generative lexicon attempts to spread the semantic load across all constituents of the utterance. Central to the philosophical perspective of GL are two major lines of inquiry: (1) How is it that we are able to deploy a finite number of words in our language in an unbounded number of contexts? (2) Is lexical information and the representations used in composing meanings separable from our commonsense knowledge?

Linguistic categories include

Computational lexicology is a branch of computational linguistics, which is concerned with the use of computers in the study of lexicon. It has been more narrowly described by some scholars as the use of computers in the study of machine-readable dictionaries. It is distinguished from computational lexicography, which more properly would be the use of computers in the construction of dictionaries, though some researchers have used computational lexicography as synonymous.

Language resource management - Lexical markup framework, is the International Organization for Standardization ISO/TC37 standard for natural language processing (NLP) and machine-readable dictionary (MRD) lexicons. The scope is standardization of principles and methods relating to language resources in the contexts of multilingual communication.

<i>Aspects of the Theory of Syntax</i>

Aspects of the Theory of Syntax is a book on linguistics written by American linguist Noam Chomsky, first published in 1965. In Aspects, Chomsky presented a deeper, more extensive reformulation of transformational generative grammar (TGG), a new kind of syntactic theory that he had introduced in the 1950s with the publication of his first book, Syntactic Structures. Aspects is widely considered to be the foundational document and a proper book-length articulation of Chomskyan theoretical framework of linguistics. It presented Chomsky's epistemological assumptions with a view to establishing linguistic theory-making as a formal discipline comparable to physical sciences, i.e. a domain of inquiry well-defined in its nature and scope. From a philosophical perspective, it directed mainstream linguistic research away from behaviorism, constructivism, empiricism and structuralism and towards mentalism, nativism, rationalism and generativism, respectively, taking as its main object of study the abstract, inner workings of the human mind related to language acquisition and production.

TimeML is a set of rules for encoding documents electronically. It is defined in the TimeML Specification version 1.2.1 developed by several efforts, led in large part by the Laboratory for Linguistics and Computation at Brandeis University.

ISO 24617-1:2009, ISO-TimeML is the International Organization for Standardization ISO/TC37 standard for time and event markup and annotation. The scope is standardization of principles and methods relating to the annotation of temporal events in the contexts of electronic documentation and language.

Temporal annotation is the study of how to automatically add semantic information regarding time to natural language documents. It plays a role in natural language processing and computational linguistics.

Bonnie Jean Dorr is an American computer scientist specializing in natural language processing and machine translation. She is a professor emerita of computer science and linguistics at the University of Maryland, College Park, an associate director and senior research scientist at the Florida Institute for Human and Machine Cognition, and the former president of the Association for Computational Linguistics.

In linguistics, the syntax–semantics interface is the interaction between syntax and semantics. Its study encompasses phenomena that pertain to both syntax and semantics, with the goal of explaining correlations between form and meaning. Specific topics include scope, binding, and lexical semantic properties such as verbal aspect and nominal individuation, semantic macroroles, and unaccusativity.

References

  1. Pustejovsky, J. (James) Library of Congress Authorities
  2. James Pustejovsky (December 1991). "The generative lexicon". Computational Linguistics . 17 (4): 409–441. ISSN   0891-2017. Wikidata   Q81546543.