Automatic acquisition of subcategorization frames from tagged text

Published 1 January 1991

Michael R. Brent, Robert C. Berwick

Citations87

TL;DR

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.

Abstract

This paper describes an implemented program that takes a tagged text corpus and generates a partial list of the subcategorization frames in which each verb occurs. The completeness of the output list increases monotonically with the total occurrences of each verb in the training corpus. False positive rates are one to three percent. Five subcategorization frames are currently detected and we foresee no impediment to detecting many more. Ultimately, we expect to provide a large subcategorization dictionary to the NLP community and to train dictionaries for specific corpora.

Keywords

Computer Science

Word association norms, mutual information, and lexicography

3,674 Citations1990Kenneth Church, Patrick Hanks

Language AcquisitionThe Structural Sources of Verb Meanings

1,773 Citations1990Lila R. Gleitman

The MIT Press eBooksLearnability and Cognition

1,443 Citations2013Steven Pinker

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.

View PDF

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.

View PDF

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.

View PDF

Parsing the LOB corpus

84 Citations1990Carl G. de Marcken

A rapid and robust parsing system currently used to learn from large bodies of unedited text, which contains a multivalued part-of-speech disambiguator and a novel parser employing bottom-up recognition to find the constituent phrases of larger structures that might be too difficult to analyze.

View PDF

Deducing linguistic structure from the statistics of large corpora

63 Citations1990Eric Brill, David M. Magerman +2 more

The Knowledge Bank (The Ohio State University)In a Manner of Speaking

63 Citations1971Arnold M. Zwicky

View PDF

Automatic semantic classification of verbs from their syntactic contexts

17 Citations1991Michael R. Brent

An implemented program that automatically classifies verbs into those that describe only states of the world and those that describes events, such as to look, is discussed, demonstrating an important new technique for the automatic generation of lexical databases.

View PDF