What Makes Word-level Neural Machine Translation Hard: A Case Study on English-German Translation
Traditional machine translation systems often require heavy feature engineering and the combination of multiple techniques for solving different subproblems. In recent years, several end-to-end learning architectures based on recurrent neural networks have been proposed. Unlike traditional systems, Neural Machine Translation (NMT) systems learn the parameters of the model and require only minimal preprocessing. Memory and time constraints allow to take only a fixed number of words into account, which leads to the out-of-vocabulary (OOV) problem. In this work, we analyze why the OOV problem arises and why it is considered a serious problem in German. We study the effectiveness of compound word splitters for alleviating the OOV problem, resulting in a 2.5+ BLEU points improvement over a baseline on the WMT{'}14 German-to-English translation task. For English-to-German translation, we use target-side compound splitting through a special syntax during training that allows the model to merge compound words and gain 0.2 BLEU points.
Code (0)
등록된 구현이 없습니다.
Tasks
Feature EngineeringMachine TranslationNMTTranslationSimilar Papers 제목 키워드 기반
Understanding Pure Character-Based Neural Machine Translation: The Case of Translating Finnish into English
Recent work has shown that deeper character-based neural machine translation (NMT) models can outperform subword-based models. However, it is still unclear what makes deeper character-based models successful. In this pap…
Machine TranslationNMTTranslationFrom Words to Sentences: A Progressive Learning Approach for Zero-resource Machine Translation with Visual Pivots
The neural machine translation model has suffered from the lack of large-scale parallel corpora. In contrast, we humans can learn multi-lingual translations even without parallel texts by referring our languages to the e…
Machine TranslationSentenceTranslationWord TranslationMeasuring Machine Translation Errors in New Domains
We develop two techniques for analyzing the effect of porting a machine translation system to a new domain. One is a macro-level analysis that measures how domain shift affects corpus-level evaluation; the second is a mi…
ArticlesDomain AdaptationMachine TranslationTranslationCombining Subword Representations into Word-level Representations in the Transformer Architecture
In Neural Machine Translation, using word-level tokens leads to degradation in translation quality. The dominant approaches use subword-level tokens, but this increases the length of the sequences and makes it difficult …
Machine TranslationPOSTranslationAttention Focusing for Neural Machine Translation by Bridging Source and Target Embeddings
In neural machine translation, a source sequence of words is encoded into a vector from which a target sequence is generated in the decoding phase. Differently from statistical machine translation, the associations betwe…
Machine TranslationSentenceTranslationWord Embeddings