Work

A plethora of methods for learning English countability

Year: 2003

Type: conference-paper

Abstract: This paper compares a range of methods for classifying words based on linguistic diagnostics, focusing on the task of learning countabilities for English nouns. We propose two basic approaches to feature representation: distribution-based representation, which simply looks at the distribution of features in the corpus data, and agreement-based representation which analyses the level of token-wise agreement between multiple preprocessor systems. We additionally compare a single multiclass classifier architecture with a suite of binary classifiers, and combine analyses from multiple preprocessors. Finally, we present and evaluate a feature selection method.

Source: Conference on Empirical Methods in Natural Language Processing (EMNLP)

DOI: 10.3115/1119355.1119365

Authors: Timothy Baldwin, Francis Bond

Institutions: Stanford University, NTT (Japan)

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: bronze

Funder: National Science Foundation

Award: Idiomatic Language: Multiword Expressions