paper-with-me

Papers

Learning from others' mistakes: Finetuning machine translation models with span-level error annotations

2024-10-21 · Lily H. Zhang, Hamid Dadkhahi, Mara Finkelstein, Firas Trabelsi, Jiaming Luo, Markus Freitag

Despite growing interest in incorporating feedback to improve language models, most efforts focus only on sequence-level annotations. In this work, we explore the potential of utilizing fine-grained span-level annotations from offline datasets to improve model quality. We develop a simple finetuning algorithm, called Training with Annotations (TWA), to directly train machine translation models on such annotated data. TWA utilizes targeted span-level error information while also flexibly learning what to penalize within a span. Moreover, TWA considers the overall trajectory of a sequence when deciding which non-error spans to utilize as positive signals. Experiments on English-German and Chinese-English machine translation show that TWA outperforms baselines such as Supervised FineTuning on sequences filtered for quality and Direct Preference Optimization on pairs constructed from the same data.

📄 PDF Abstract BibTeX arXiv:2410.16509

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationTranslation

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Correct-and-Memorize: Learning to Translate from Interactive Revisions

2019-07-08 · Rongxiang Weng, Hao Zhou, Shu-Jian Huang, Lei LI 외

State-of-the-art machine translation models are still not on par with human translators. Previous work takes human interactions into the neural machine translation process to obtain improved results in target languages. …

Machine TranslationTranslation

NRC-CNRC Machine Translation Systems for the 2021 AmericasNLP Shared Task

2021-06-01 · NAACL (AmericasNLP) 2021 6 · Rebecca Knowles, Darlene Stewart, Samuel Larkin, Patrick Littell

We describe the NRC-CNRC systems submitted to the AmericasNLP shared task on machine translation. We submitted systems translating from Spanish into Wixárika, Nahuatl, Rarámuri, and Guaraní. Our best neural machine trans…

Machine TranslationTranslation

Multitask Finetuning for Improving Neural Machine Translation in Indian Languages

2021-12-03 · Shaily Desai, Atharva Kshirsagar, Manisha Marathe

Transformer based language models have led to impressive results across all domains in Natural Language Processing. Pretraining these models on language modeling tasks and finetuning them on downstream tasks such as Text…

Causal Language ModelingLanguage ModelingLanguage ModellingMachine Translation+4

Character-level NMT and language similarity

2023-08-08 · Josef Jon, Ondřej Bojar

We explore the effectiveness of character-level neural machine translation using Transformer architecture for various levels of language similarity and size of the training dataset on translation between Czech and Croati…

Machine TranslationNMTSegmentationTranslation

On Instruction-Finetuning Neural Machine Translation Models

2024-10-07 · Vikas Raunak, Roman Grundkiewicz, Marcin Junczys-Dowmunt

In this work, we introduce instruction finetuning for Neural Machine Translation (NMT) models, which distills instruction following capabilities from Large Language Models (LLMs) into orders-of-magnitude smaller NMT mode…

Domain AdaptationInstruction FollowingMachine TranslationNMT+1