Overcoming the Curse of Sentence Length for Neural Machine Translation using Automatic Segmentation
| Autor: | Kyunghyun Cho, Dzmitry Bahdanau, Jean Pouget-Abadie, Bart van Merriënboer, Yoshua Bengio |
|---|---|
| Rok vydání: | 2014 |
| Předmět: |
Curse
Phrase Machine translation Artificial neural network Sentence length business.industry Computer science media_common.quotation_subject computer.software_genre Translation (geometry) Automatic segmentation Quality (business) Artificial intelligence business computer Sentence Natural language processing media_common |
| Zdroj: | SSST@EMNLP |
| DOI: | 10.3115/v1/w14-4009 |
| Popis: | The authors of (Cho et al., 2014a) have shown that the recently introduced neural network translation systems suffer from a significant drop in translation quality when translating long sentences, unlike existing phrase-based translation systems. In this paper, we propose a way to address this issue by automatically segmenting an input sentence into phrases that can be easily translated by the neural network translation model. Once each segment has been independently translated by the neural machine translation model, the translated clauses are concatenated to form a final translation. Empirical results show a significant improvement in translation quality for long sentences. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|