paper-with-me

홈 › Papers

Repairing Pronouns in Translation with BERT-Based Post-Editing

2021-03-23 · Reid Pryzant

Pronouns are important determinants of a text's meaning but difficult to translate. This is because pronoun choice can depend on entities described in previous sentences, and in some languages pronouns may be dropped when the referent is inferrable from the context. These issues can lead Neural Machine Translation (NMT) systems to make critical errors on pronouns that impair intelligibility and even reinforce gender bias. We investigate the severity of this pronoun issue, showing that (1) in some domains, pronoun choice can account for more than half of a NMT systems' errors, and (2) pronouns have a disproportionately large impact on perceived translation quality. We then investigate a possible solution: fine-tuning BERT on a pronoun prediction task using chunks of source-side sentences, then using the resulting classifier to repair the translations of an existing NMT model. We offer an initial case study of this approach for the Japanese-English language pair, observing that a small number of translations are significantly improved according to human evaluators.

📄 PDF Abstract BibTeX arXiv:2103.12838

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationNMTTranslation

Methods 이 논문이 사용한 방법론

Repair 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Weight Decay 설명 없음
WordPiece 설명 없음
Adam 설명 없음
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…

Similar Papers 제목 키워드 기반

Scalable Cross Lingual Pivots to Model Pronoun Gender for Translation

2020-06-16 · Kellie Webster, Emily Pitler

Machine translation systems with inadequate document understanding can make errors when translating dropped or neutral pronouns into languages with gendered pronouns (e.g., English). Predicting the underlying gender of t…

document understandingMachine TranslationSentenceTranslation

Interactive Post-Editing for Verbosity Controlled Translation

2022-10-01 · COLING 2022 10 · Prabhakar Gupta, Anil Nelakanti, Grant M. Berry, Abhishek Sharma

We explore Interactive Post-Editing (IPE) models for human-in-loop translation to help correct translation errors and rephrase it with a desired style variation. We specifically study verbosity for style variations and b…

Machine TranslationTranslation

Discourse Dependency: A Continuous Criterion for Translation Difficulty

2026-09-04 · Ahrii Kim, Chanjun Park, Seong-heum Kim arxiv

Recent calls for harder machine translation benchmarks have not clarified what difficulty should mean. We argue that one meaningful and currently unmeasured axis is referential reach, the distance a segment must look bac…

Machine Translation

Unbabel's Submission to the WMT2019 APE Shared Task: BERT-based Encoder-Decoder for Automatic Post-Editing

2019-05-30 · WS 2019 8 · António V. Lopes, M. Amin Farajian, Gonçalo M. Correia, Jonay Trenous 외

This paper describes Unbabel's submission to the WMT2019 APE Shared Task for the English-German language pair. Following the recent rise of large, powerful, pre-trained models, we adapt the BERT pretrained model to perfo…

Automatic Post-EditingDecoderMachine TranslationNMT+1

A Simple and Effective Approach to Automatic Post-Editing with Transfer Learning

2019-07-01 · ACL 2019 7 · Gon{\c{c}}alo M. Correia, Andr{\'e} F. T. Martins

Automatic post-editing (APE) seeks to automatically refine the output of a black-box machine translation (MT) system through human post-edits. APE systems are usually trained by complementing human post-edited data with …

Automatic Post-EditingDecoderGPUMachine Translation+2