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

## TL;DR

This paper introduces an automatic frame analysis system for French encyclopedic texts, jointly optimizing frame detection and semantic role labeling, with detailed evaluations on task complexity and feature selection.

## Contribution

It presents a novel integrated sequence labeling model for joint frame and role analysis in French texts, with comprehensive evaluation of task complexity.

## Key findings

- Effective joint frame and role analysis achieved
- Detailed insights into feature importance and data challenges
- Evaluation of task complexity from multiple dimensions

## 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.