paper-with-me

홈 › Papers

Fine-Grained Attention Mechanism for Neural Machine Translation

2018-03-30 · Heeyoul Choi, Kyunghyun Cho, Yoshua Bengio

Neural machine translation (NMT) has been a new paradigm in machine translation, and the attention mechanism has become the dominant approach with the state-of-the-art records in many language pairs. While there are variants of the attention mechanism, all of them use only temporal attention where one scalar value is assigned to one context vector corresponding to a source word. In this paper, we propose a fine-grained (or 2D) attention mechanism where each dimension of a context vector will receive a separate attention score. In experiments with the task of En-De and En-Fi translation, the fine-grained attention method improves the translation quality in terms of BLEU score. In addition, our alignment analysis reveals how the fine-grained attention mechanism exploits the internal structure of context vectors.

📄 PDF Abstract BibTeX arXiv:1803.11407

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationNMTTranslation

Similar Papers 제목 키워드 기반

Lost in the Source Language: How Large Language Models Evaluate the Quality of Machine Translation

2024-01-12 · Xu Huang, Zhirui Zhang, Xiang Geng, Yichao Du 외

This study investigates how Large Language Models (LLMs) leverage source and reference data in machine translation evaluation task, aiming to better understand the mechanisms behind their remarkable performance in this t…

Machine TranslationTranslation

Fine Grained Human Evaluation for English-to-Chinese Machine Translation: A Case Study on Scientific Text

2021-09-13 · Ming Liu, He Zhang, Guanhao Wu

Recent research suggests that neural machine translation (MT) in the news domain has reached human-level performance, but for other professional domains, it is far below the level. In this paper, we conduct a fine-graine…

Machine TranslationNMTTranslation

Improving Attention Modeling with Implicit Distortion and Fertility for Machine Translation

2016-12-01 · COLING 2016 12 · Shi Feng, Shujie Liu, Nan Yang, Mu Li 외

In neural machine translation, the attention mechanism facilitates the translation process by producing a soft alignment between the source sentence and the target sentence. However, without dedicated distortion and fert…

DecoderMachine TranslationSentenceTranslation

Attention based Sequence to Sequence Learning for Machine Translation of Low Resourced Indic Languages -- A case of Sanskrit to Hindi

2021-09-07 · Vishvajit Bakarola, Jitendra Nasriwala

Deep Learning techniques are powerful in mimicking humans in a particular set of problems. They have achieved a remarkable performance in complex learning tasks. Deep learning inspired Neural Machine Translation (NMT) is…

Machine TranslationNMTTranslation

Name Translation based on Fine-grained Named Entity Recognition in a Single Language

2016-05-01 · LREC 2016 5 · Kugatsu Sadamitsu, Itsumi Saito, Taichi Katayama, Hisako Asano 외

We propose named entity abstraction methods with fine-grained named entity labels for improving statistical machine translation (SMT). The methods are based on a bilingual named entity recognizer that uses a monolingual …

Machine Translationnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)+2