Compară metode
Examinează metodele selectate una lângă alta; rândurile care diferă sunt evidențiate.
| Sumarizare multilingvă de text× | Transformer multilingv× | |
|---|---|---|
| Domeniu | Învățare profundă | Învățare profundă |
| Familie | Machine learning | Machine learning |
| Anul apariției≠ | 2020–2021 | 2019–2020 |
| Autorul original≠ | Multiple groups; popularized via mBART (Liu et al., 2020) and mT5 (Xue et al., 2021) | Devlin et al. (mBERT); Conneau et al. (XLM-R) |
| Tip≠ | Seq2seq / encoder-decoder fine-tuning for summarization across languages | Pre-trained cross-lingual language model |
| Sursa seminală≠ | Xue, L., Constant, N., Roberts, A., Kale, M., Al-Rfou, R., Siddhant, A., Barua, A., & Raffel, C. (2021). mT5: A Massively Multilingual Pre-Trained Text-to-Text Transformer. Proceedings of NAACL-HLT 2021, pp. 483–498. Association for Computational Linguistics. link ↗ | Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Proceedings of NAACL-HLT 2019, pp. 4171–4186. Association for Computational Linguistics. DOI ↗ |
| Denumiri alternative | cross-lingual summarization, multilingual abstractive summarization, multilingual extractive summarization, multilingual seq2seq summarization | multilingual LM, cross-lingual transformer, mBERT-style model, multilingual pre-trained model |
| Înrudite | 4 | 4 |
| Rezumat≠ | Multilingual text summarization applies pre-trained multilingual encoder-decoder models — such as mT5 or mBART — to generate concise summaries of documents written in many languages, either within the same language (monolingual) or across languages (cross-lingual). Fine-tuning these models on multilingual summarization benchmarks like XL-Sum enables coverage of dozens of languages with a single model. | A multilingual transformer is a pre-trained language model built on the transformer architecture and trained jointly on text from dozens to over one hundred languages. Models such as mBERT and XLM-RoBERTa learn shared cross-lingual representations, enabling zero-shot or few-shot transfer: a model fine-tuned on English data can often be applied directly to French, German, Arabic, or Chinese without language-specific labels. |
| ScholarGateSet de date ↗ |
|
|