paper-with-me

홈 › Papers

Prevent the Language Model from being Overconfident in Neural Machine Translation

2021-05-24 · ACL 2021 5 · Mengqi Miao, Fandong Meng, Yijin Liu, Xiao-Hua Zhou, Jie zhou

The Neural Machine Translation (NMT) model is essentially a joint language model conditioned on both the source sentence and partial translation. Therefore, the NMT model naturally involves the mechanism of the Language Model (LM) that predicts the next token only based on partial translation. Despite its success, NMT still suffers from the hallucination problem, generating fluent but inadequate translations. The main reason is that NMT pays excessive attention to the partial translation while neglecting the source sentence to some extent, namely overconfidence of the LM. Accordingly, we define the Margin between the NMT and the LM, calculated by subtracting the predicted probability of the LM from that of the NMT model for each token. The Margin is negatively correlated to the overconfidence degree of the LM. Based on the property, we propose a Margin-based Token-level Objective (MTO) and a Margin-based Sentencelevel Objective (MSO) to maximize the Margin for preventing the LM from being overconfident. Experiments on WMT14 English-to-German, WMT19 Chinese-to-English, and WMT14 English-to-French translation tasks demonstrate the effectiveness of our approach, with 1.36, 1.50, and 0.63 BLEU improvements, respectively, compared to the Transformer baseline. The human evaluation further verifies that our approaches improve translation adequacy as well as fluency.

📄 PDF Abstract BibTeX arXiv:2105.11098

Code (1)

Mlair77/nmt_adequacy 공식 구현 pytorch

Tasks

HallucinationLanguage ModelingLanguage ModellingMachine TranslationNMTSentenceTranslation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Attention 설명 없음
Residual Connection 설명 없음
Adam 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

Fine-Tuning Large Language Models to Translate: Will a Touch of Noisy Data in Misaligned Languages Suffice?

2024-04-22 · Dawei Zhu, Pinzhen Chen, Miaoran Zhang, Barry Haddow 외

Traditionally, success in multilingual machine translation can be attributed to three key factors in training data: large volume, diverse translation directions, and high quality. In the current practice of fine-tuning l…

Machine TranslationTranslation

Scalable Machine Translation in Memory Constrained Environments

2016-10-06 · Paul Baltescu

Machine translation is the discipline concerned with developing automated tools for translating from one human language to another. Statistical machine translation (SMT) is the dominant paradigm in this field. In SMT, tr…

Machine TranslationTranslation

Neural Machine Translation with Byte-Level Subwords

2019-09-07 · Changhan Wang, Kyunghyun Cho, Jiatao Gu

Almost all existing machine translation models are built on top of character-based vocabularies: characters, subwords or words. Rare characters from noisy text or character-rich languages such as Japanese and Chinese how…

Machine TranslationTranslation

Translate-R1: Cost-Aware Translation Tool Use via Reinforcement Learning

2026-06-05 · Pratik Jayarao, Chaitanya Dwivedi, Himanshu Gupta, Neeraj Varshney 외 arxiv

The performance gap across languages in LLMs is well documented, and closing it natively requires pretraining or fine-tuning on corpora that, for most languages, do not exist. Translation offers an alternative: convertin…

Reinforcement Learning

Alternated Training with Synthetic and Authentic Data for Neural Machine Translation

2021-06-16 · Findings (ACL) 2021 8 · Rui Jiao, Zonghan Yang, Maosong Sun, Yang Liu

While synthetic bilingual corpora have demonstrated their effectiveness in low-resource neural machine translation (NMT), adding more synthetic data often deteriorates translation performance. In this work, we propose al…

Low Resource Neural Machine TranslationLow-Resource Neural Machine TranslationMachine TranslationNMT+1