Comparer des méthodes
Examinez les méthodes sélectionnées côte à côte ; les lignes qui diffèrent sont mises en évidence.
| Synthèse multi-documents× | Embeddings BERT× | |
|---|---|---|
| Domaine | Fouille de textes | Fouille de textes |
| Famille | Process / pipeline | Process / pipeline |
| Année d'origine≠ | — | 2019 |
| Auteur d'origine≠ | — | Devlin, Chang, Lee & Toutanova (Google AI) |
| Type≠ | NLP text-summarization task | Contextual transformer text-representation method |
| Source fondatrice≠ | Erkan, G. & Radev, D.R. (2004). LexRank: Graph-Based Lexical Centrality as Salience in Text Summarization. Journal of Artificial Intelligence Research, 22, 457-479. link ↗ | Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. NAACL-HLT, 4171-4186. DOI ↗ |
| Alias | MDS, Çok Belgeli Özetleme (Multi-Document Summarization), multi-source summarization | contextual embeddings, transformer embeddings, BERT Tabanlı Metin Gömülmeleri |
| Apparentées≠ | 5 | 4 |
| Résumé≠ | Multi-document summarization (MDS) is a natural-language-processing task that condenses a cluster of related documents into a single comprehensive, coherent, and non-redundant summary. Formally described by Erkan and Radev (2004) through the LexRank algorithm, MDS is used in news cluster analysis, systematic literature reviews, and research synthesis to give readers a unified view of information spread across multiple sources. | BERT-based text embeddings, introduced by Devlin and colleagues at Google AI in 2019, turn text into context-sensitive dense vectors using a bidirectional Transformer encoder. Because the meaning of a word shifts with its context, BERT produces richer representations than static methods such as Word2Vec or topic models like LDA. |
| ScholarGateJeu de données ↗ |
|
|