When Word Pairs Matter - Analysis of the English-Slovak Evaluation Dataset

Varování

Publikace nespadá pod Filozofickou fakultu, ale pod Fakultu informatiky. Oficiální stránka publikace je na webu muni.cz.
Autoři

DENISOVÁ Michaela RYCHLÝ Pavel

Rok publikování 2021
Druh Článek ve sborníku
Konference Proceedings of the Fifteenth Workshop on Recent Advances in Slavonic Natural Languages Processing, RASLAN 2021
Fakulta / Pracoviště MU

Fakulta informatiky

Citace
www
Klíčová slova Cross-lingual word embeddings; Ground truth dictionary; Evaluation; English; Slovak
Popis Cross-lingual word embeddings facilitate the transfer of lexical knowledge across languages, and they are mainly used for finding transla- tion equivalents. Translation equivalents obtained in this way are usually evaluated with the help of ground truth dictionaries. However, the evalu- ation process, including the ground truth dictionaries, differs from model to model, impeding the correct interpretation of the results. Therefore, in this paper, we provide a thorough analysis of the English-Slovak ground truth dictionary and employ our analysis in evaluating two cross-lingual word embedding models. We show that word pairs choice is an important factor when accurately reflecting the model’s performance.
Související projekty:

Používáte starou verzi internetového prohlížeče. Doporučujeme aktualizovat Váš prohlížeč na nejnovější verzi.