Word Ordering Without Syntax
| Autor: | Stuart M. Shieber, Alexander M. Rush, Allen Schmaltz |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Computation and Language business.industry Computer science Heuristic 02 engineering and technology computer.software_genre Syntax Task (project management) 03 medical and health sciences 0302 clinical medicine Order (business) Simple (abstract algebra) 030221 ophthalmology & optometry 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence Language model business Computation and Language (cs.CL) computer Word (computer architecture) Sentence Natural language processing |
| Zdroj: | EMNLP |
| DOI: | 10.18653/v1/d16-1255 |
| Popis: | Recent work on word ordering has argued that syntactic structure is important, or even required, for effectively recovering the order of a sentence. We find that, in fact, an n-gram language model with a simple heuristic gives strong results on this task. Furthermore, we show that a long short-term memory (LSTM) language model is even more effective at recovering order, with our basic model outperforming a state-of-the-art syntactic model by 11.5 BLEU points. Additional data and larger beams yield further gains, at the expense of training and search time. EMNLP 2016 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|