paper-with-me

홈 › Papers

Enabling Multi-Source Neural Machine Translation By Concatenating Source Sentences In Multiple Languages

2017-02-20 · MTSummit 2017 9 · Raj Dabre, Fabien Cromieres, Sadao Kurohashi

In this paper, we explore a simple solution to "Multi-Source Neural Machine Translation" (MSNMT) which only relies on preprocessing a N-way multilingual corpus without modifying the Neural Machine Translation (NMT) architecture or training procedure. We simply concatenate the source sentences to form a single long multi-source input sentence while keeping the target side sentence as it is and train an NMT system using this preprocessed corpus. We evaluate our method in resource poor as well as resource rich settings and show its effectiveness (up to 4 BLEU using 2 source languages and up to 6 BLEU using 5 source languages). We also compare against existing methods for MSNMT and show that our solution gives competitive results despite its simplicity. We also provide some insights on how the NMT system leverages multilingual information in such a scenario by visualizing attention.

📄 PDF Abstract BibTeX arXiv:1702.06135

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationNMTSentenceTranslation

Similar Papers 제목 키워드 기반

Relay Decoding: Concatenating Large Language Models for Machine Translation

2024-05-05 · Chengpeng Fu, Xiaocheng Feng, Yichong Huang, Wenshuai Huo 외

Leveraging large language models for machine translation has demonstrated promising results. However, it does require the large language models to possess the capability of handling both the source and target languages i…

Machine TranslationTranslation

Neural Machine Translation with Source Dependency Representation

2017-09-01 · EMNLP 2017 9 · Kehai Chen, Rui Wang, Masao Utiyama, Lemao Liu 외

Source dependency information has been successfully introduced into statistical machine translation. However, there are only a few preliminary attempts for Neural Machine Translation (NMT), such as concatenating represen…

Machine TranslationNMTTranslation

Is Encoder-Decoder Redundant for Neural Machine Translation?

2022-10-21 · Yingbo Gao, Christian Herold, Zijian Yang, Hermann Ney

Encoder-decoder architecture is widely adopted for sequence-to-sequence modeling tasks. For machine translation, despite the evolution from long short-term memory networks to Transformer networks, plus the introduction a…

DecoderLanguage ModelingLanguage ModellingMachine Translation+2

Sentence Concatenation Approach to Data Augmentation for Neural Machine Translation

2021-04-17 · NAACL 2021 4 · Seiichiro Kondo, Kengo Hotate, Masahiro Kaneko, Mamoru Komachi

Neural machine translation (NMT) has recently gained widespread attention because of its high translation accuracy. However, it shows poor performance in the translation of long sentences, which is a major issue in low-r…

Data AugmentationMachine TranslationNMTSentence+1

CoMeT: Towards Code-Mixed Translation Using Parallel Monolingual Sentences

2021-06-01 · NAACL (CALCS) 2021 6 · Devansh Gautam, Prashant Kodali, Kshitij Gupta, Anmol Goel 외

Code-mixed languages are very popular in multilingual societies around the world, yet the resources lag behind to enable robust systems on such languages. A major contributing factor is the informal nature of these langu…

Machine TranslationTranslation