| Auteur | Rechercher : Lo, Chi-kiu1; Rechercher : Simard, Michel1 |
|---|
| Affiliation | - Conseil national de recherches du Canada. Technologies numériques
|
|---|
| Format | Texte, Article |
|---|
| Conférence | 23rd Conference on Computational Natural Language Learning, CoNLL 2019, November 3-4, 2019, Hong Kong, China |
|---|
| Résumé | We present a fully unsupervised crosslingual semantic textual similarity (STS) metric, based on contextual embeddings extracted from BERT - Bidirectional Encoder Representations from Transformers (Devlin et al., 2019). The goal of crosslingual STS is to measure to what degree two segments of text in different languages express the same meaning. Not only is it a key task in crosslingual natural language understanding (XLU), it is also particularly useful for identifying parallel resources for training and evaluating downstream multilingual natural language processing (NLP) applications, such as machine translation. Most previous crosslingual STS methods relied heavily on existing parallel resources, thus leading to a circular dependency problem. With the advent of massively multilingual context representation models such as BERT, which are trained on the concatenation of non-parallel data from each language, we show that the deadlock around parallel resources can be broken. We perform intrinsic evaluations on crosslingual STS data sets and extrinsic evaluations on parallel corpus filtering and human translation equivalence assessment tasks. Our results show that the unsupervised crosslingual STS metric using BERT without fine-tuning achieves performance on par with supervised or weakly supervised approaches. |
|---|
| Date de publication | 2019-11-03 |
|---|
| Maison d’édition | Association for Computational Linguistics |
|---|
| Dans | |
|---|
| Langue | anglais |
|---|
| Publications évaluées par des pairs | Oui |
|---|
| Exporter la notice | Exporter en format RIS |
|---|
| Signaler une correction | Signaler une correction (s'ouvre dans un nouvel onglet) |
|---|
| Identificateur de l’enregistrement | 042d0e4b-593d-40d8-8d93-2c984a9f0aa2 |
|---|
| Enregistrement créé | 2021-03-15 |
|---|
| Enregistrement modifié | 2021-03-15 |
|---|
