Natural Language Processing with Small Feed-Forward Networks
| Autor: | Ji Ma, Slav Petrov, Emily Pitler, Ryan McDonald, David J. Weiss, Jan A. Botha, Alexandru Salcianu, Anton Bakalov |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
FOS: Computer and information sciences
Range (mathematics) Computer Science - Computation and Language Artificial neural network SIMPLE (military communications protocol) Computer science Distributed computing I.2.7 68T50 Feed forward Computer Science - Neural and Evolutionary Computing Neural and Evolutionary Computing (cs.NE) Computation and Language (cs.CL) |
| Zdroj: | EMNLP |
| DOI: | 10.48550/arxiv.1708.00214 |
| Popis: | We show that small and shallow feed-forward neural networks can achieve near state-of-the-art results on a range of unstructured and structured language processing tasks while being considerably cheaper in memory and computational requirements than deep recurrent models. Motivated by resource-constrained environments like mobile phones, we showcase simple techniques for obtaining such small neural network models, and investigate different tradeoffs when deciding how to allocate a small memory budget. Comment: EMNLP 2017 short paper |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|