IRIT-IRIS at CL-SciSumm 2019: Matching Citances with their Intended Reference Text Spans from the Scientific Literature - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

IRIT-IRIS at CL-SciSumm 2019: Matching Citances with their Intended Reference Text Spans from the Scientific Literature

Résumé

The CL-SCisumm track provides a framework to evaluate systems summarising scientific papers. It includes datasets and metrics provided by the organisers. The track comprises three tasks: (1a) identifying the spans of text in the referred document reflecting citing ext spans i.e., citances), (1b) classifying discourse facets ofthe cited text spans, and (2) generating a short structured summary. For the 2019 edi-tion, we focused our work on the task 1a. This report presents our proposed approachfor this task. We submitted 15 runs corresponding to different configurations of theparameters involved in our approach.

Mots clés

Fichier principal
Vignette du fichier
pitarch_26391.pdf (306.93 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02947789 , version 1 (24-09-2020)

Identifiants

  • HAL Id : hal-02947789 , version 1
  • OATAO : 26391

Citer

Yoann Pitarch, Karen Pinel-Sauvagnat, Gilles Hubert, Guillaume Cabanac, Ophélie Fraisier. IRIT-IRIS at CL-SciSumm 2019: Matching Citances with their Intended Reference Text Spans from the Scientific Literature. 4th Joint Workshop on Bibliometric-enhanced Information Retrieval and Natural Language Processing for Digital Libraries co-located with the 42nd International ACM SIGIR Conference (BIRNDL 2019), Jul 2019, Paris, France. pp.208-213. ⟨hal-02947789⟩
57 Consultations
24 Téléchargements

Partager

Gmail Facebook X LinkedIn More