TermITH-Eval : a French Standard-Based Resource for Keyphrase Extraction Evaluation

Adrien Bougouin (1) , Sabine Barreaux (2) , Laurent Romary (3, 4) , Florian Boudin (1) , Béatrice Daille (1)

1 LINA - Laboratoire d'Informatique de Nantes Atlantique
2 INIST - Institut de l'information scientifique et technique
3 ALPAGE - Analyse Linguistique Profonde à Grande Echelle ; Large-scale deep linguistic processing
4 HU Berlin - Humboldt-Universität zu Berlin = Humboldt University of Berlin = Université Humboldt de Berlin

Keyphrase extraction is the task of finding phrases that represent the important content of a document. The main aim of keyphrase extraction is to propose textual units that represent the most important topics developed in a document. The output keyphrases of automatic keyphrase extraction methods for test documents are typically evaluated by comparing them to manually assigned reference keyphrases. Each output keyphrase is considered correct if it matches one of the reference keyphrases. However, the choice of the appropriate textual unit (keyphrase) for a topic is sometimes subjective and evaluating by exact matching underestimates the performance. This paper presents a dataset of evaluation scores assigned to automatically extracted keyphrases by human evaluators. Along with the reference keyphrases, the manual evaluations can be used to validate new evaluation measures. Indeed, an evaluation measure that is highly correlated to the manual evaluation is appropriate for the evaluation of automatic keyphrase extraction methods.

Keywords: Automatic evaluation; Structured resource; TermITH-Eval; Keyphrase extraction

Domains: Computer Science [cs]; Information Retrieval [cs.IR]; Document and Text Processing

Adrien Bougouin, Sabine Barreaux, Laurent Romary, Florian Boudin, Béatrice Daille. TermITH-Eval : a French Standard-Based Resource for Keyphrase Extraction Evaluation. LREC - Language Resources and Evaluation Conference, May 2016, Potoroz, Slovenia. pp.1924-1927. ⟨hal-01693805⟩