Comparer des méthodes
Examinez les méthodes sélectionnées côte à côte ; les lignes qui diffèrent sont mises en évidence.
| Interrogation en langue multiple× | Classification basée sur BERT× | |
|---|---|---|
| Domaine | Apprentissage profond | Apprentissage profond |
| Famille | Machine learning | Machine learning |
| Année d'origine≠ | 2018–2020 | 2019 |
| Auteur d'origine≠ | Multiple groups; popularised via mBERT (Devlin et al., 2019) and XLM-R (Conneau et al., 2020) | Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (Google AI Language) |
| Type≠ | Extractive / generative QA across multiple languages | Pre-trained language model with fine-tuning |
| Source fondatrice≠ | Artetxe, M., Ruder, S., & Yogatama, D. (2020). On the cross-lingual transferability of monolingual representations. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (pp. 4623–4637). ACL. DOI ↗ | Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of NAACL-HLT 2019 (pp. 4171–4186). Association for Computational Linguistics. DOI ↗ |
| Alias | cross-lingual question answering, multilingual QA, multilingual MRC, cross-lingual machine reading comprehension | BERT classifier, BERT fine-tuning for classification, BERT text classification, BERT-CLS |
| Apparentées | 4 | 4 |
| Résumé≠ | Multilingual question answering (QA) enables a model to read a passage and answer questions in multiple languages, often by fine-tuning a cross-lingual pretrained transformer such as mBERT or XLM-R on an annotated QA dataset in one language and transferring that capability zero-shot or few-shot to other languages. It is the standard approach for building multilingual reading-comprehension and open-domain QA systems. | BERT-based Classification fine-tunes Google's Bidirectional Encoder Representations from Transformers model on a labelled text dataset, replacing the generic pre-trained head with a task-specific classification layer. It exploits deep bidirectional context from hundreds of millions of pre-trained parameters to deliver state-of-the-art accuracy on short- and medium-length text classification tasks with relatively modest amounts of labelled data. |
| ScholarGateJeu de données ↗ |
|
|