Jämför metoder
Granska de valda metoderna sida vid sida; rader som skiljer sig är markerade.
| Domänadaptiv Doc2Vec× | Doc2Vec× | |
|---|---|---|
| Ämnesområde≠ | Djupinlärning | Textutvinning |
| Familj≠ | Machine learning | Process / pipeline |
| Ursprungsår≠ | 2014 (Doc2Vec); domain-adaptive application mid-2010s onward | 2014 |
| Upphovsperson≠ | Le & Mikolov (Doc2Vec); domain adaptation literature (Blitzer, Daumé III, and others) | Quoc V. Le & Tomas Mikolov |
| Typ≠ | Unsupervised / domain-adaptive document embedding | Document-embedding representation learning |
| Ursprungskälla≠ | Le, Q. V., & Mikolov, T. (2014). Distributed representations of sentences and documents. Proceedings of the 31st International Conference on Machine Learning (ICML 2014), PMLR 32(2), 1188–1196. link ↗ | Le, Q. V. & Mikolov, T. (2014). Distributed Representations of Sentences and Documents. Proceedings of the 31st International Conference on Machine Learning (ICML), 1188-1196. link ↗ |
| Alias≠ | domain-adapted Doc2Vec, cross-domain paragraph vector, domain-adaptive PV-DM, domain-adaptive PV-DBOW | paragraph vector, document embeddings, Doc2Vec Belge Gömülmeleri |
| Närliggande≠ | 5 | 4 |
| Sammanfattning≠ | Domain-adaptive Doc2Vec adapts the Paragraph Vector (Doc2Vec) framework so that document embeddings learned on a source domain transfer effectively to a target domain. By aligning the representation space across domains during or after training, the model produces embeddings that are informative on both, enabling cross-domain classification, sentiment analysis, and retrieval with limited target-domain labels. | Doc2Vec, also known as Paragraph Vector, is a representation-learning method introduced by Le and Mikolov (2014) that maps whole documents to fixed-length dense vectors. These vectors place similar documents close together in space, supporting document comparison and classification. |
| ScholarGateDatamängd ↗ |
|
|