paper-with-me

Papers

Improving the Lexical Ability of Pretrained Language Models for Unsupervised Neural Machine Translation

2021-03-18 · NAACL 2021 4 · Alexandra Chronopoulou, Dario Stojanovski, Alexander Fraser

Successful methods for unsupervised neural machine translation (UNMT) employ crosslingual pretraining via self-supervision, often in the form of a masked language modeling or a sequence generation task, which requires the model to align the lexical- and high-level representations of the two languages. While cross-lingual pretraining works for similar languages with abundant corpora, it performs poorly in low-resource and distant languages. Previous research has shown that this is because the representations are not sufficiently aligned. In this paper, we enhance the bilingual masked language model pretraining with lexical-level information by using type-level cross-lingual subword embeddings. Empirical results demonstrate improved performance both on UNMT (up to 4.5 BLEU) and bilingual lexicon induction using our method compared to a UNMT baseline.

📄 PDF Abstract BibTeX arXiv:2103.10531

Code (1)

alexandra-chron/lexical_xlm_relm 공식 구현 pytorch

Tasks

Bilingual Lexicon InductionLanguage ModelingLanguage ModellingMachine TranslationMasked Language ModelingTranslation

Similar Papers 제목 키워드 기반

MANTIS at TSAR-2022 Shared Task: Improved Unsupervised Lexical Simplification with Pretrained Encoders

2022-12-19 · Xiaofei Li, Daniel Wiechmann, Yu Qiao, Elma Kerz

In this paper we present our contribution to the TSAR-2022 Shared Task on Lexical Simplification of the EMNLP 2022 Workshop on Text Simplification, Accessibility, and Readability. Our approach builds on and extends the u…

Language ModelingLanguage ModellingLexical SimplificationNatural Language Inference+3

The Impact of Syntactic and Semantic Proximity on Machine Translation with Back-Translation

2024-03-26 · Nicolas Guerin, Shane Steinert-Threlkeld, Emmanuel Chemla

Unsupervised on-the-fly back-translation, in conjunction with multilingual pretraining, is the dominant method for unsupervised neural machine translation. Theoretically, however, the method should not work in general. W…

Machine TranslationTranslationUnsupervised Machine Translation

Incremental Neural Lexical Coherence Modeling

2020-12-01 · COLING 2020 8 · Sungho Jeon, Michael Strube

Pretrained language models, neural models pretrained on massive amounts of data, have established the state of the art in a range of NLP tasks. They are based on a modern machine-learning technique, the Transformer which…

Language ModelingLanguage Modelling

Multilingual Lexical Simplification via Paraphrase Generation

2023-07-28 · Kang Liu, Jipeng Qiang, Yun Li, Yunhao Yuan 외

Lexical simplification (LS) methods based on pretrained language models have made remarkable progress, generating potential substitutes for a complex word through analysis of its contextual surroundings. However, these m…

DiversityLexical SimplificationMachine TranslationParaphrase Generation+2

Iterative Constrained Back-Translation for Unsupervised Domain Adaptation of Machine Translation

2022-10-01 · COLING 2022 10 · Hongxiao Zhang, Hui Huang, Jiale Gao, Yufeng Chen 외

Back-translation has been proven to be effective in unsupervised domain adaptation of neural machine translation (NMT). However, the existing back-translation methods mainly improve domain adaptability by generating in-d…

Domain AdaptationMachine TranslationNMTSentence+3