paper-with-me

홈 › Papers

Modeling Target-Side Inflection in Neural Machine Translation

2017-07-19 · WS 2017 9 · Aleš Tamchyna, Marion Weller-Di Marco, Alexander Fraser

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.

📄 PDF Abstract BibTeX arXiv:1707.06012

Code (0)

등록된 구현이 없습니다.

Tasks

LEMMAMachine TranslationNMTPOSTAGTranslation

Methods 이 논문이 사용한 방법론

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

Modeling Word Formation in English--German Neural Machine Translation

2020-07-01 · ACL 2020 6 · Marion Weller-Di Marco, Alex Fraser, er

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+1

Neural Machine Translation Doesn't Translate Gender Coreference Right Unless You Make It

2020-10-11 · Danielle Saunders, Rosie Sallis, Bill Byrne

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 TranslationNMTSentenceTranslation

Neural Machine Translation Doesn’t Translate Gender Coreference Right Unless You Make It

2020-12-01 · GeBNLP (COLING) 2020 12 · Danielle Saunders, Rosie Sallis, Bill Byrne

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 TranslationNMTSentenceTranslation

Fine-grained Gender Control in Machine Translation with Large Language Models

2024-07-21 · Minwoo Lee, Hyukhun Koh, Minsung Kim, Kyomin Jung

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 TranslationSentenceTranslation

Rule-based Morphological Inflection Improves Neural Terminology Translation

2021-09-10 · EMNLP 2021 11 · Weijia Xu, Marine Carpuat

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