paper-with-me

Papers

Augmenting Statistical Machine Translation with Subword Translation of Out-of-Vocabulary Words

2018-08-16 · Nelson F. Liu, Jonathan May, Michael Pust, Kevin Knight

Most statistical machine translation systems cannot translate words that are unseen in the training data. However, humans can translate many classes of out-of-vocabulary (OOV) words (e.g., novel morphological variants, misspellings, and compounds) without context by using orthographic clues. Following this observation, we describe and evaluate several general methods for OOV translation that use only subword information. We pose the OOV translation problem as a standalone task and intrinsically evaluate our approaches on fourteen typologically diverse languages across varying resource levels. Adding OOV translators to a statistical machine translation system yields consistent BLEU gains (0.5 points on average, and up to 2.0) for all fourteen languages, especially in low-resource scenarios.

📄 PDF Abstract BibTeX arXiv:1808.05700

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationTranslation

Similar Papers 제목 키워드 기반

TranSFormer: Slow-Fast Transformer for Machine Translation

2023-05-26 · Bei Li, Yi Jing, Xu Tan, Zhen Xing 외

Learning multiscale Transformer models has been evidenced as a viable approach to augmenting machine translation systems. Prior research has primarily focused on treating subwords as basic units in developing such system…

Machine TranslationTranslation

Word, Subword or Character? An Empirical Study of Granularity in Chinese-English NMT

2017-11-13 · Yining Wang, Long Zhou, Jiajun Zhang, Cheng-qing Zong

Neural machine translation (NMT), a new approach to machine translation, has been proved to outperform conventional statistical machine translation (SMT) across a variety of language pairs. Translation is an open-vocabul…

Machine TranslationNMTTranslation

Bilingual Subword Segmentation for Neural Machine Translation

2020-12-01 · COLING 2020 8 · Hiroyuki Deguchi, Masao Utiyama, Akihiro Tamura, Takashi Ninomiya 외

This paper proposed a new subword segmentation method for neural machine translation, {``}Bilingual Subword Segmentation,{''} which tokenizes sentences to minimize the difference between the number of subword units in a …

Machine TranslationSegmentationSentenceTranslation

Incorporating Word and Subword Units in Unsupervised Machine Translation Using Language Model Rescoring

2019-08-16 · WS 2019 8 · Zihan Liu, Yan Xu, Genta Indra Winata, Pascale Fung

This paper describes CAiRE's submission to the unsupervised machine translation track of the WMT'19 news shared task from German to Czech. We leverage a phrase-based statistical machine translation (PBSMT) model and a pr…

Language ModelingLanguage ModellingMachine TranslationNMT+2

Extended Parallel Corpus for Amharic-English Machine Translation

2021-04-08 · LREC 2022 6 · Andargachew Mekonnen Gezmu, Andreas Nürnberger, Tesfaye Bayu Bati

This paper describes the acquisition, preprocessing, segmentation, and alignment of an Amharic-English parallel corpus. It will be helpful for machine translation of a low-resource language, Amharic. We freely released t…

Language ModelingLanguage ModellingMachine TranslationTranslation