Modeling Target-Side Inflection in Neural Machine Translation
NMT systems have problems with large vocabulary sizes. Byte-pair encoding (BPE) is a popular approach to solving this problem, but while BPE allows the system to generate any target-side word, it does not enable effective generalization over the rich vocabulary in morphologically rich languages with strong inflectional phenomena. We introduce a simple approach to overcome this problem by training a system to produce the lemma of a word and its morphologically rich POS tag, which is then followed by a deterministic generation step. We apply this strategy for English-Czech and English-German translation scenarios, obtaining improvements in both settings. We furthermore show that the improvement is not due to only adding explicit morphological information.
Code (0)
등록된 구현이 없습니다.
Tasks
LEMMAMachine TranslationNMTPOSTAGTranslationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Modeling Word Formation in English--German Neural Machine Translation
This paper studies strategies to model word formation in NMT using rich linguistic information, namely a word segmentation approach that goes beyond splitting into substrings by considering fusional morphology. Our lingu…
Machine TranslationMorphological AnalysisNMTSegmentation+1Neural Machine Translation Doesn't Translate Gender Coreference Right Unless You Make It
Neural Machine Translation (NMT) has been shown to struggle with grammatical gender that is dependent on the gender of human referents, which can cause gender bias effects. Many existing approaches to this problem seek t…
Machine TranslationNMTSentenceTranslationNeural Machine Translation Doesn’t Translate Gender Coreference Right Unless You Make It
Neural Machine Translation (NMT) has been shown to struggle with grammatical gender that is dependent on the gender of human referents, which can cause gender bias effects. Many existing approaches to this problem seek t…
Machine TranslationNMTSentenceTranslationFine-grained Gender Control in Machine Translation with Large Language Models
In machine translation, the problem of ambiguously gendered input has been pointed out, where the gender of an entity is not available in the source sentence. To address this ambiguity issue, the task of controlled trans…
Machine TranslationSentenceTranslationRule-based Morphological Inflection Improves Neural Terminology Translation
Current approaches to incorporating terminology constraints in machine translation (MT) typically assume that the constraint terms are provided in their correct morphological forms. This limits their application to real-…
Domain AdaptationLEMMAMachine TranslationMorphological Inflection+2