Informace o publikaci
When Word Pairs Matter - Analysis of the English-Slovak Evaluation Dataset
| Autoři | |
|---|---|
| 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 | |
| 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: |