paper-with-me

홈 › Papers

An Empirical study of Unsupervised Neural Machine Translation: analyzing NMT output, model's behavior and sentences' contribution

2023-12-19 · Isidora Chara Tourni, Derry Wijaya

Unsupervised Neural Machine Translation (UNMT) focuses on improving NMT results under the assumption there is no human translated parallel data, yet little work has been done so far in highlighting its advantages compared to supervised methods and analyzing its output in aspects other than translation accuracy. We focus on three very diverse languages, French, Gujarati, and Kazakh, and train bilingual NMT models, to and from English, with various levels of supervision, in high- and low- resource setups, measure quality of the NMT output and compare the generated sequences' word order and semantic similarity to source and reference sentences. We also use Layer-wise Relevance Propagation to evaluate the source and target sentences' contribution to the result, expanding the findings of previous works to the UNMT paradigm.

📄 PDF Abstract BibTeX arXiv:2312.12588

Code (0)

등록된 구현이 없습니다.

Tasks

Low Resource Neural Machine TranslationLow-Resource Neural Machine TranslationMachine TranslationNMTSemantic SimilaritySemantic Textual SimilarityTranslation

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
Multi-Head Attention 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
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

A Multilingual View of Unsupervised Machine Translation

2020-02-07 · Findings of the Association for Computational Linguistics 2020 · Xavier Garcia, Pierre Foret, Thibault Sellam, Ankur P. Parikh

We present a probabilistic framework for multilingual neural machine translation that encompasses supervised and unsupervised setups, focusing on unsupervised translation. In addition to studying the vanilla case where t…

Machine TranslationTranslationUnsupervised Machine Translation

Study on Unsupervised Statistical Machine Translation for Backtranslation

2019-09-01 · RANLP 2019 9 · Anush Kumar, Nihal V. Nayak, Ch, Aditya ra 외

Machine Translation systems have drastically improved over the years for several language pairs. Monolingual data is often used to generate synthetic sentences to augment the training data which has shown to improve the …

Machine TranslationTranslationUnsupervised Machine Translation

Cross-lingual Supervision Improves Unsupervised Neural Machine Translation

2020-04-07 · NAACL 2021 4 · Mingxuan Wang, Hongxiao Bai, Hai Zhao, Lei LI

Neural machine translation~(NMT) is ineffective for zero-resource languages. Recent works exploring the possibility of unsupervised neural machine translation (UNMT) with only monolingual data can achieve promising resul…

Machine TranslationNMTTranslation

Unsupervised Bilingual Word Embedding Agreement for Unsupervised Neural Machine Translation

2019-07-01 · ACL 2019 7 · Haipeng Sun, Rui Wang, Kehai Chen, Masao Utiyama 외

Unsupervised bilingual word embedding (UBWE), together with other technologies such as back-translation and denoising, has helped unsupervised neural machine translation (UNMT) achieve remarkable results in several langu…

DecoderDenoisingMachine TranslationTranslation

Advances and Challenges in Unsupervised Neural Machine Translation

2021-04-01 · EACL 2021 2 · Rui Wang, Hai Zhao

Unsupervised cross-lingual language representation initialization methods, together with mechanisms such as denoising and back-translation, have advanced unsupervised neural machine translation (UNMT), which has achieved…

DenoisingMachine TranslationTranslation