Verbal chunk extraction in French using limited resources

TL;DR

This paper presents a method for extracting French verbal chunks using limited resources, combining morphological rules, local grammar, and heuristics tested on a real corpus.

Contribution

It introduces a resource-efficient approach for French verbal chunk extraction utilizing simple rules and heuristics, suitable for limited data scenarios.

Findings

Effective extraction of verbal chunks demonstrated on corpus

Relies on limited lexical and morphological information

Achieves promising results with simple heuristic methods

Abstract

A way of extracting French verbal chunks, inflected and infinitive, is explored and tested on effective corpus. Declarative morphological and local grammar rules specifying chunks and some simple contextual structures are used, relying on limited lexical information and some simple heuristic/statistic properties obtained from restricted corpora. The specific goals, the architecture and the formalism of the system, the linguistic information on which it relies and the obtained results on effective corpus are presented.