Võrdle meetodeid
Vaata valitud meetodeid kõrvuti; erinevad read on esile tõstetud.
| Long Short-Term Memory (LSTM)× | Sentence Embeddings× | |
|---|---|---|
| Valdkond | Süvaõpe | Süvaõpe |
| Perekond | Machine learning | Machine learning |
| Tekkeaasta≠ | 1997 | 2015–2019 |
| Looja≠ | Hochreiter, S. & Schmidhuber, J. | Kiros et al. (Skip-Thought, 2015); Reimers & Gurevych (Sentence-BERT, 2019) |
| Tüüp≠ | Recurrent neural network with gated memory cells | Representation learning / embedding |
| Algallikas≠ | Hochreiter, S. & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780. 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 ↗ |
| Rööpnimetused | LSTM, LSTM network, LSTM-RNN, long short-term memory RNN | sentence vectors, sentence representations, SBERT, semantic sentence encoding |
| Seotud | 4 | 4 |
| Kokkuvõte≠ | Long Short-Term Memory (LSTM) is a gated recurrent neural network architecture introduced by Hochreiter and Schmidhuber in 1997. It was designed to learn dependencies across long sequences by using dedicated memory cells and three learned gates — forget, input, and output — that control what information is retained, updated, or passed forward at each time step. | 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. |
| ScholarGateAndmestik ↗ |
|
|