Work

FrameNet automatic analysis : a study on a French corpus of encyclopedic texts

Year: 2018

Type: preprint

Abstract: This article presents an automatic frame analysis system evaluated on a corpus of French encyclopedic history texts annotated according to the FrameNet formalism. The chosen approach relies on an integrated sequence labeling model which jointly optimizes frame identification and semantic role segmentation and identification. The purpose of this study is to analyze the task complexity from several dimensions. Hence we provide detailed evaluations from a feature selection point of view and from the data point of view.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.1812.08044

Authors: Marzinotto, Gabriel, Damnati, Géraldine, Bechet, Frederic

Institutions: Orange (France), Laboratoire d’Informatique Fondamentale de Marseille

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W2903697179

Cites:

Cited by:

Related to: 10