Unsupervised Lexical Learning with Categorical Grammars Using the LLL Corpus

Stephen Watkinson; Suresh Manandhar

doi:10.1007/3-540-40030-3_14

Unsupervised Lexical Learning with Categorical Grammars Using the LLL Corpus

Stephen Watkinson, Suresh Manandhar

Computer Science

Research output: Contribution to conference › Paper › peer-review

Abstract

In this paper we report on an unsupervised approach to learning Categorial Grammar (CG) lexicons. The learner is provided with a set of possible lexical CG categories, the forward and backward application rules of CG and unmarked positive only corpora. Using the categories and rules, the sentences from the corpus are probabilistically parsed. The parses of this example and the set of parses of earlier examples in the corpus are used to build a lexicon and annotate the corpus. We report the results from experiments on two generated corpora and also on the more complicated LLL corpus, that contains examples from subsets of English syntax. These show that the system is able to generate reasonable lexicons and provide accurately parsed corpora in the process. We also discuss ways in which the approach can be scaled up to deal with larger and more diverse corpora.

Original language	Undefined/Unknown
Pages	218-236
DOIs	https://doi.org/10.1007/3-540-40030-3_14
Publication status	Published - 1999

Access to Document

10.1007/3-540-40030-3_14

http://link.springer.de/link/service/series/0558/bibs/1925/19250218.htm

Cite this

@conference{423ee143ed98477d8821fb589b7dc756,

title = "Unsupervised Lexical Learning with Categorical Grammars Using the LLL Corpus",

abstract = "In this paper we report on an unsupervised approach to learning Categorial Grammar (CG) lexicons. The learner is provided with a set of possible lexical CG categories, the forward and backward application rules of CG and unmarked positive only corpora. Using the categories and rules, the sentences from the corpus are probabilistically parsed. The parses of this example and the set of parses of earlier examples in the corpus are used to build a lexicon and annotate the corpus. We report the results from experiments on two generated corpora and also on the more complicated LLL corpus, that contains examples from subsets of English syntax. These show that the system is able to generate reasonable lexicons and provide accurately parsed corpora in the process. We also discuss ways in which the approach can be scaled up to deal with larger and more diverse corpora. ",

author = "Stephen Watkinson and Suresh Manandhar",

year = "1999",

doi = "10.1007/3-540-40030-3_14",

language = "Undefined/Unknown",

pages = "218--236",

}

TY - CONF

T1 - Unsupervised Lexical Learning with Categorical Grammars Using the LLL Corpus

AU - Watkinson, Stephen

AU - Manandhar, Suresh

PY - 1999

Y1 - 1999

N2 - In this paper we report on an unsupervised approach to learning Categorial Grammar (CG) lexicons. The learner is provided with a set of possible lexical CG categories, the forward and backward application rules of CG and unmarked positive only corpora. Using the categories and rules, the sentences from the corpus are probabilistically parsed. The parses of this example and the set of parses of earlier examples in the corpus are used to build a lexicon and annotate the corpus. We report the results from experiments on two generated corpora and also on the more complicated LLL corpus, that contains examples from subsets of English syntax. These show that the system is able to generate reasonable lexicons and provide accurately parsed corpora in the process. We also discuss ways in which the approach can be scaled up to deal with larger and more diverse corpora.

AB - In this paper we report on an unsupervised approach to learning Categorial Grammar (CG) lexicons. The learner is provided with a set of possible lexical CG categories, the forward and backward application rules of CG and unmarked positive only corpora. Using the categories and rules, the sentences from the corpus are probabilistically parsed. The parses of this example and the set of parses of earlier examples in the corpus are used to build a lexicon and annotate the corpus. We report the results from experiments on two generated corpora and also on the more complicated LLL corpus, that contains examples from subsets of English syntax. These show that the system is able to generate reasonable lexicons and provide accurately parsed corpora in the process. We also discuss ways in which the approach can be scaled up to deal with larger and more diverse corpora.

U2 - 10.1007/3-540-40030-3_14

DO - 10.1007/3-540-40030-3_14

M3 - Paper

SP - 218

EP - 236

ER -