Jämför metoder
Granska de valda metoderna sida vid sida; rader som skiljer sig är markerade.
| Semi-supervised Question Answering× | Finjusterad frågesvarsmodell× | |
|---|---|---|
| Ämnesområde | Djupinlärning | Djupinlärning |
| Familj | Machine learning | Machine learning |
| Ursprungsår≠ | 2006–2020 | 2016–2019 |
| Upphovsperson≠ | Multiple (Chapelle et al.; Zhu; Clark et al. for NLP applications) | Devlin et al. (BERT); Rajpurkar et al. (SQuAD benchmark) |
| Typ≠ | Semi-supervised learning applied to extractive/generative QA | Transfer learning / fine-tuning for extractive or generative QA |
| Ursprungskälla≠ | Clark, K., Luong, M.-T., Le, Q. V., & Manning, C. D. (2020). ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators. In Proceedings of ICLR 2020. 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, 4171–4186. DOI ↗ |
| Alias | Semi-supervised QA, Self-training for QA, Pseudo-labeled Question Answering, SSL-QA | fine-tuned QA, neural QA with fine-tuning, extractive QA fine-tuning, reading comprehension fine-tuning |
| Närliggande≠ | 6 | 5 |
| Sammanfattning≠ | Semi-supervised question answering (QA) trains a model on a small labeled set of question-answer pairs, then generates pseudo-labels on a large unlabeled corpus and retrains iteratively. This self-training loop dramatically increases effective training data without the cost of full manual annotation, achieving strong performance on reading comprehension, open-domain QA, and machine reading tasks. | Fine-Tuned Question Answering adapts a large pre-trained language model — such as BERT, RoBERTa, or a GPT-family model — to answer natural-language questions over a given context passage or knowledge base. The model learns to locate answer spans or generate free-form answers by continuing training on labeled QA pairs after general-purpose pre-training. |
| ScholarGateDatamängd ↗ |
|
|