Learning Methods for Combining Linguistic Indicators to Classify Verbs

1997/09/12 by Eric V. Siegel, Siegel, Eric V.
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #cmp-lg #cs.CL

paper · pdf · doi:10.48550/arxiv.cmp-lg/9709002

7 pages, Latex, in the Proceedings of the Second Conference on Empirical Methods in Natural Language Processing, Providence, Rhode Island, 1997

openalex publication_date 1997/09/12 · arxiv created 1997/09/13 · arxiv updated 2009/11/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Fourteen linguistically-motivated numerical indicators are evaluated for their ability to categorize verbs as either states or events. The values for each indicator are computed automatically across a corpus of text. To improve classification performance, machine learning techniques are employed to combine multiple indicators. Three machine learning methods are compared for this task: decision tree induction, a genetic algorithm, and log-linear regression.

Related

• Gathering Statistics to Aspectually Classify Sentences with a Genetic Algorithm
• Classifying text using machine learning models and determining conversation drift
• Improving Statistical Language Model Performance with Automatically\n Generated Word Hierarchies
• Probing Internal Representations of Multi-Word Verbs in Large Language Models
• Language Semantics Interpretation with an Interaction-based Recurrent Neural Networks