Porovnat metody
Prohlédněte si vybrané metody vedle sebe; řádky, které se liší, jsou zvýrazněny.
| Generování přirozeného jazyka× | Model sekvence-sekvence× | |
|---|---|---|
| Obor≠ | Dolování textu | Hluboké učení |
| Rodina≠ | Process / pipeline | Machine learning |
| Rok vzniku≠ | 1970s (rule-based origins); 2000s (probabilistic); 2017+ (neural/transformer era) | 2014 |
| Tvůrce≠ | Reiter & Dale (classical pipeline, 2000); Gatt & Krahmer (modern survey, 2018) | Sutskever, I.; Cho, K. |
| Typ≠ | NLP generative task — structured data to natural language | Encoder-decoder neural network (deep learning) |
| Původní zdroj≠ | Gatt, A. & Krahmer, E. (2018). Survey of the State of the Art in Natural Language Generation: Core Tasks, Applications and Evaluation. Journal of Artificial Intelligence Research, 61, 65-170. link ↗ | Sutskever, I., Vinyals, O. & Le, Q. V. (2014). Sequence to Sequence Learning with Neural Networks. NeurIPS. link ↗ |
| Další názvy | NLG, data-to-text, text generation, Doğal Dil Üretimi (NLG) | Dizi-Dizi Modeli (Seq2Seq — Encoder-Decoder), encoder-decoder model, seq2seq, sequence to sequence learning |
| Příbuzné≠ | 7 | 5 |
| Shrnutí≠ | Natural Language Generation (NLG) is the branch of natural language processing that automatically produces fluent, human-readable text from structured data, knowledge graphs, or semantic representations. Formalised in the classical pipeline by Reiter and Dale (2000) and surveyed comprehensively by Gatt and Krahmer (2018), NLG powers applications ranging from automated financial reporting and weather bulletins to data storytelling and conversational agents. | The sequence-to-sequence (Seq2Seq) model, introduced by Sutskever, Vinyals and Le and by Cho and colleagues in 2014, is an encoder-decoder neural network that maps a variable-length input sequence to a variable-length output sequence. It is the foundation of machine translation, text summarization, dialogue systems and code generation. |
| ScholarGateDatová sada ↗ |
|
|