Evaluating Diversity of Multiword Expressions in Annotated Text

Adam Lion-Bouton (1, 2) , Yağmur Öztürk (1, 2) , Agata Savary (3, 4) , Jean-Yves Antoine (2, 5)

1 LIFAT - Laboratoire d'Informatique Fondamentale et Appliquée de Tours
2 BDTLN - Bases de données et traitement des langues naturelles
3 STL - Sciences et Technologies des Langues - LISN
4 LISN - Laboratoire Interdisciplinaire des Sciences du Numérique
5 LIFO - Laboratoire d'Informatique Fondamentale d'Orléans

Diversity can be decomposed into three distinct concepts, namely: variety, balance and disparity. This paper borrows from the extensive formalization and measures of diversity developed in ecology in order to evaluate the variety and balance of multiword expression annotation produced by automatic annotation systems. The measures of richness, normalized richness, and two variations of Hill's evenness are considered in this paper. We observe how these measures behave against increasingly smaller samples of gold annotations of multiword expressions and use their comportment to validate or invalidate their pertinence for multiword expressions in annotated texts. We apply the validated measures to annotations in 14 languages produced by systems during the PARSEME shared task on automatic identification of multiword expressions and on the gold versions of the corpora. We also explore the limits of such evaluation by studying the impact of lemmatization errors in the Turkish corpus used in the shared task.

Mots clés: multiword expressions; diversity; variety; balance

Domaines: Informatique et langage [cs.CL]; Linguistique

Adam Lion-Bouton, Yağmur Öztürk, Agata Savary, Jean-Yves Antoine. Evaluating Diversity of Multiword Expressions in Annotated Text. International Committee on Computational Linguistics (COLING), International Committee on Computational Linguistics, Oct 2022, Gyeongju, South Korea. pp.3285-3295. ⟨hal-04468662⟩