Word Representation Models for Morphologically Rich Languages in Neural Machine Translation
Dealing with the complex word forms in morphologically rich languages is an open problem in language processing, and is particularly important in translation. In contrast to most modern neural systems of translation, which discard the identity for rare words, in this paper we propose several architectures for learning word representations from character and morpheme level word decompositions. We incorporate these representations in a novel machine translation model which jointly learns word alignments and translations via a hard attention mechanism. Evaluating on translating from several morphologically rich languages into English, we show consistent improvements over strong baseline methods, of between 1 and 1.5 BLEU points.
Code (0)
등록된 구현이 없습니다.
Tasks
Hard AttentionMachine TranslationTranslationSimilar Papers 제목 키워드 기반
A Hybrid Morpheme-Word Representation for Machine Translation of Morphologically Rich Languages
We propose a language-independent approach for improving statistical machine translation for morphologically rich languages using a hybrid morpheme-word representation where the basic unit of translation is the morpheme,…
Machine TranslationSentenceTranslationAn Evaluation of Subword Segmentation Strategies for Neural Machine Translation of Morphologically Rich Languages
Byte-Pair Encoding (BPE) (Sennrich et al., 2016) has become a standard pre-processing step when building neural machine translation systems. However, it is not clear whether this is an optimal strategy in all settings. W…
Language ModelingLanguage ModellingMachine TranslationTranslationComparison of Turkish Word Representations Trained on Different Morphological Forms
Increased popularity of different text representations has also brought many improvements in Natural Language Processing (NLP) tasks. Without need of supervised data, embeddings trained on large corpora provide us meanin…
Language ModelingLanguage ModellingLEMMAtext-classification+1Improved Transition-Based Parsing by Modeling Characters instead of Words with LSTMs
We present extensions to a continuous-state dependency parsing method that makes it applicable to morphologically rich languages. Starting with a high-performance transition-based parser that uses long short-term memory …
Dependency ParsingCross-Lingual Word Embeddings for Morphologically Rich Languages
Cross-lingual word embedding models learn a shared vector space for two or more languages so that words with similar meaning are represented by similar vectors regardless of their language. Although the existing models a…
Cross-Lingual Word EmbeddingsTranslationWord EmbeddingsWord Translation