Work

Supersense tagging of unknown nouns using semantic similarity

Year: 2005

Type: conference-paper

Abstract: The limited coverage of lexical-semantic resources is a significant problem for NLP systems which can be alleviated by automatically classifying the unknown words. Supersense tagging assigns unknown nouns one of 26 broad semantic categories used by lexicographers to organise their manual insertion into WORDNET. Ciaramita and Johnson (2003) present a tagger which uses synonym set glosses as annotated training examples. We describe an unsupervised approach, based on vector-space similarity, which does not require annotated examples but significantly outperforms their tagger. We also demonstrate the use of an extremely large shallow-parsed corpus for calculating vector-space semantic similarity.

Source: Annual Meeting of the Association for Computational Linguistics (ACL)

DOI: 10.3115/1219840.1219844

Author: James R. Curran

Institution: The University of Sydney

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: bronze

Funder: Australian Research Council

Award: Ask the Net: Intelligent Natural Language Learning