Automatic acquisition of hyponyms from large text corpora
Published 1 January 1992Open access
Marti A. Hearst
Citations3,283
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A set of lexico-syntactic patterns that are easily recognizable, that occur frequently and across text genre boundaries, and that indisputably indicate the lexical relation of interest are identified.
Abstract
We describe a method for the automatic acquisition of the hyponymy lexical relation from unrestricted text. Two goals motivate the approach: (i) avoidance of the need for pre-encoded knowledge and (ii) applicability across a wide range of text. We identify a set of lexico-syntactic patterns that are easily recognizable, that occur frequently and across text genre boundaries, and that indisputably indicate the lexical relation of interest. We describe a method for discovering these patterns and suggest that other lexical relations will also be acquirable in this way. A subset of the acquisition algorithm is implemented and the results are used to augment and critique the structure of a large hand-built thesaurus. Extensions and applications to areas such as information retrieval are suggested.
Keywords
Computer Science
International Journal of LexicographyIntroduction to WordNet: An On-line Lexical Database<sup>*</sup>
4,207 Citations1990George A. Miller, Richard Beckwith +3 more
Standard alphabetical procedures for organizing lexical information put together words that are spelled alike and scatter words with similar or related meanings haphazardly through the list.
Lexical cohesion computed by thesaural relations as an indicator of the structure of text
941 Citations1991Jane Morris, Graeme Hirst
A practical part-of-speech tagger
632 Citations1992Doug Cutting, Julian Kupiec +2 more
An implementation of a part-of-speech tagger based on a hidden Markov model that enables robust and accurate tagging with few resource requirements and accuracy exceeds 96%.
Noun classification from predicate-argument structures
543 Citations1990Donald Hindle
The resulting quasi-semantic classification of nouns demonstrates the plausibility of the distributional hypothesis, and has potential application to a variety of tasks, including automatic indexing, resolving nominal compounds, and determining the scope of modification.
Studies in linguistics and philosophyProviding Machine Tractable Dictionary Tools
186 Citations1993Yorick Wilks
Automatically extracting and representing collocations for language generation
140 Citations1990Frank Smadja, Kathleen McKeown
A program is described, Xtract, that automatically acquires a range of collocations from large textual corpora and how they can be represented in a flexible lexicon using a unification based formalism is described.
Automatic acquisition of subcategorization frames from untagged text
105 Citations1991Michael R. Brent
An implemented program that takes a raw, untagged text corpus as its only input and generates a partial list of verbs occurring in the text and the subcategorization frames (SFs) in which they occur to provide a large SF dictionary to the NLP community and to train dictionaries for specific corpora.
Semantically significant patterns in dictionary definitions
100 Citations1986Judith Markowitz, Thomas Ahlswede +1 more
Methods for finding taxonomy and set-membership relationships, recognizing nouns that ordinarily represent human beings, and identifying active and stative verbs and adjectives are described.
Disambiguating prepositional phrase attachments by using on-line dictionary definitions
98 Citations1987Karen Jensen, Jean-Louis Binot
Automatic acquisition of subcategorization frames from tagged text
87 Citations1991Michael R. Brent, Robert C. Berwick
An implemented program that takes a tagged text corpus and generates a partial list of the subcategorization frames in which each verb occurs and expects to provide a large subc categorization dictionary to the NLP community and to train dictionaries for specific corpora.
Machine TranslationProviding machine tractable dictionary tools
81 Citations1990Yorick Wilks, Dan Fass +4 more
This paper discusses three different but related large-scale computational methods to transform Mrds into Mtds, the Longman Dictionary of Contemporary English (Ldoce), which is a statistical approach and requires some handcoding of initial information but is largely automatic.
Processing dictionary definitions with phrasal pattern hierarchies
74 Citations1987Hiyan Alshawi
This paper shows how dictionary word sense definitions can be analysed by applying a hierarchy of phrasal patterns, ensuring that reasonable incomplete analyses of the definitions are produced when more complete analyses are not possible, resulting in a relatively robust analysis mechanism.
Extraction of semantic information from an ordinary English dictionary and its evaluation
64 Citations1988Jun-ichi Nakramura, Makoto Nagao
The automatic extraction of semantic information especially semantic relationships between words, from an odinary English dictionary is described and the result of the extraction has been compared with semantic information (semantic markers) which the magnetic tape version of LDOCE contains.
Acquiring lexical knowledge from text: a case study
51 Citations1988Paul S. Jacobs, Uri Zernik
This paper describes an approach to constructing new lexical entries in a gradual process by analyzing a sequence of example texts to permit the graceful tolerance of new words while enabling the automated extension of the lexicon.
Parsing vs. text processing in the analysis of dictionary definitions
22 Citations1988Thomas Ahlswede, Martha Evens
This paper analyzed definitions from Webster's Seventh New Collegiate Dictionary using Sager's Linguistic String Parser and again using basic UNIX text processing utilities such as grep and awk, and discusses possible future lines of research exploiting and combining their respective strengths.
Computer aided interpretation of lexical cooccurrences
12 Citations1989Paola Velardi, Maria Teresa Pazienza
The system presented hereafter, PETRARCA, detects word cooccurrences from a large sample of press agency releases on finance and economics, and uses these associations to build a case-based semantic lexicon.
DSpace@MIT (Massachusetts Institute of Technology)Automatic acquisition and use of some of the knowledge in physics texts
6 Citations1991John Batali, Gerald Jay Sussman
An investigation of the workings of expository technical texts with the goal of being able to automatically acquire and use some of the knowledge that they contain to solve problems based on that material.