Sammenlign metoder
Gjennomgå de valgte metodene side om side; rader som avviker, er uthevet.
| Finjustert Doc2Vec× | Doc2Vec× | |
|---|---|---|
| Fagfelt≠ | Dyp læring | Tekstutvinning |
| Familie≠ | Machine learning | Process / pipeline |
| Opprinnelsesår≠ | 2014 (base); fine-tuning practice ca. 2015 | 2014 |
| Opphavsperson≠ | Le, Q. V. & Mikolov, T. (Doc2Vec base); fine-tuning practice adopted by the NLP community ca. 2015–2017 | Quoc V. Le & Tomas Mikolov |
| Type≠ | Representation learning / transfer learning | Document-embedding representation learning |
| Opprinnelig kilde≠ | 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≠ | fine-tuned Paragraph Vector, domain-adapted Doc2Vec, PV fine-tuning, Doc2Vec transfer learning | paragraph vector, document embeddings, Doc2Vec Belge Gömülmeleri |
| Relaterte≠ | 5 | 4 |
| Sammendrag≠ | Fine-Tuned Doc2Vec adapts a pre-trained Paragraph Vector (Doc2Vec) model by continuing its training on a target corpus, producing document embeddings that capture both the general language knowledge of the original training and the vocabulary and style of the new domain. It is used for text classification, semantic similarity, and clustering when labeled data are scarce but unlabeled domain text is available. | 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. |
| ScholarGateDatasett ↗ |
|
|