Retrieving collocations from text
Computational LinguisticsPublished 1 March 1993
SmadjaFrank
Citations211
SJR quartileQ1
SJR score1.15
SNIP4.16
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
Natural languages are full of collocations, recurrent combinations of words that co-occur more often than expected by chance and that correspond to arbitrary word usages.
Abstract
Natural languages are full of collocations, recurrent combinations of words that co-occur more often than expected by chance and that correspond to arbitrary word usages. Recent work in lexicograph...
Keywords
PsychologyComputer ScienceArts and Humanities
IEEE Transactions on Pattern Analysis and Machine IntelligenceA Maximum Likelihood Approach to Continuous Speech Recognition
1,220 Citations1983L.R. Bahl, Frederick Jelinek +1 more
This paper describes a number of statistical models for use in speech recognition, with special attention to determining the parameters for such models from sparse data, and describes two decoding methods appropriate for constrained artificial languages and one appropriate for more realistic decoding tasks.
A stochastic parts program and noun phrase parser for unrestricted text
974 Citations1988Kenneth Church
A program that tags each word in an input sentence with the most likely part of speech has been written and performance is encouraging; a 400-word sample is presented and is judged to be 99.5% correct.
Studies in linguistics and philosophyParsing By Chunks
878 Citations1991Steven Abney
The typical chunk consists of a single content word surrounded by a constellation of function words, matching a fixed template, and the relationships between chunks are mediated more by lexical selection than by rigid templates.
A statistical approach to language translation
269 Citations1988Peter Brown, John Cocke +5 more
An approach to automatic translation is outlined that utilizes techniques of statistical information extraction from large data bases based on the availability of pairs of large corresponding texts that are translations of each other in English and French.
The BBI Combinatory Dictionary of English: A guide to word combinations
209 Citations1986Morton Benson, Evelyn Benson +1 more
Studies in language companion seriesLexicographic Description of English
190 Citations1986Morton Benson, Evelyn Benson +1 more
The first serious attempt to describe in detail the lexical and grammatical differences between American and British English and a pioneering description of the principles concerning the treatment of fixed grammatical and lexical collocations in future general-purpose dictionaries of English.
Parsing, word associations and typical predicate-argument relations
91 Citations1989Kenneth Church, William A. Gale +2 more
This paper will attempt to show that many of these types of concerns can be addressed with syntactic methods (symbol pushing, and need not require explicit semantic interpretation), and it is possible to identify many of these interesting co-occurrence relations by computing simple summary statistics over millions of words of text.
Poor estimates of context are worse than none
62 Citations1990William A. Gale, Kenneth Church
It is found that it is possible to make useful estimates of contextual probabilities that improve performance in a spelling correction application, and it is shown that the Good-Turing method makes the use of contextual information practical for a spelling corrector.
IEEE Transactions on Information TheoryOn the relations between modeling approaches for speech recognition
37 Citations1990Y. Ephraim, L. R. Rabiner
It is shown that all three approaches can be formulated uniformly as MDI modeling approaches for simultaneous estimation of the acoustic models for all words in the vocabulary and that none of the approaches requires any model correctness assumption.
The Slavic and East European JournalLexical Functions and Language Learning
33 Citations1979Richard L. Leed, Alexander Nakhimovsky
The notion of lexical functions can be used by language teachers to help students learn proper lexical collocations and develop a richer vocabulary and is presented in three parts: first the lexico-syntactic problem facing the student is presented and how the principle of Lexical functions relates to it is shown; then examples of variousLexical functions are given; finally the illustrations are presented.
How to Compile a Bilingual Collocational Lexicon . Automatically
28 Citations1992Frank Smadja
These sentences are extracted from a corpus of the proccedings of the Canadian Parliament, also called the Hansards corpus, andSentence (If) is thus the translation in French of Sentence (le).
Types in Functional Unification Grammars
25 Citations1990Michael Elhadad
This work implements an extension of traditional functional unification based on the notions of typed features and typed constituents, and shows the advantages of this extension in the context of a grammar used for text generation.
Speech recognition with very large size dictionary
20 Citations2005Bernard Mérialdo
A new strategy is proposed, the Multi-Level Decoding (MLD), that allows to use a Very Large Size Dictionary (VLSD, size more than 100,000 words) in speech recognition and is experimented on a dictation task of French texts.