Jämför metoder
Granska de valda metoderna sida vid sida; rader som skiljer sig är markerade.
| Finjusterad frågesvarsmodell× | Meningsinbäddningar× | |
|---|---|---|
| Ämnesområde | Djupinlärning | Djupinlärning |
| Familj | Machine learning | Machine learning |
| Ursprungsår≠ | 2016–2019 | 2015–2019 |
| Upphovsperson≠ | Devlin et al. (BERT); Rajpurkar et al. (SQuAD benchmark) | Kiros et al. (Skip-Thought, 2015); Reimers & Gurevych (Sentence-BERT, 2019) |
| Typ≠ | Transfer learning / fine-tuning for extractive or generative QA | Representation learning / embedding |
| Ursprungskälla≠ | 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 ↗ | Reimers, N., & Gurevych, I. (2019). Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP), 3980–3990. DOI ↗ |
| Alias | fine-tuned QA, neural QA with fine-tuning, extractive QA fine-tuning, reading comprehension fine-tuning | sentence vectors, sentence representations, SBERT, semantic sentence encoding |
| Närliggande≠ | 5 | 4 |
| Sammanfattning≠ | 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. | Sentence Embeddings convert a sentence or short text into a single fixed-length dense vector that captures its semantic meaning. These vectors allow downstream tasks — semantic similarity, clustering, retrieval, and classification — to operate on numerical representations instead of raw text, making them one of the most versatile building blocks in modern NLP pipelines. |
| ScholarGateDatamängd ↗ |
|
|