paper-with-me

홈 › Papers

Neural Machine Translation with Characters and Hierarchical Encoding

2016-10-20 · Alexander Rosenberg Johansen, Jonas Meinertz Hansen, Elias Khazen Obeid, Casper Kaae Sønderby, Ole Winther

Most existing Neural Machine Translation models use groups of characters or whole words as their unit of input and output. We propose a model with a hierarchical char2word encoder, that takes individual characters both as input and output. We first argue that this hierarchical representation of the character encoder reduces computational complexity, and show that it improves translation performance. Secondly, by qualitatively studying attention plots from the decoder we find that the model learns to compress common words into a single embedding whereas rare words, such as names and places, are represented character by character.

📄 PDF Abstract BibTeX arXiv:1610.06550

Code (1)

Styrke/master-code 공식 구현 tf

Tasks

DecoderMachine TranslationTranslation

Similar Papers 제목 키워드 기반

On the Importance of Word Boundaries in Character-level Neural Machine Translation

2019-10-15 · WS 2019 11 · Duygu Ataman, Orhan Firat, Mattia A. Di Gangi, Marcello Federico 외

Neural Machine Translation (NMT) models generally perform translation using a fixed-size lexical vocabulary, which is an important bottleneck on their generalization capability and overall translation quality. The standa…

Machine TranslationNMTTranslation

Character-level Chinese-English Translation through ASCII Encoding

2018-05-09 · WS 2018 10 · Nikola I. Nikolov, Yuhuang Hu, Mi Xue Tan, Richard H. R. Hahnloser

Character-level Neural Machine Translation (NMT) models have recently achieved impressive results on many language pairs. They mainly do well for Indo-European language pairs, where the languages share the same writing s…

Machine TranslationNMTTranslation

Unified Embedding for Universal Multilingual Neural Machine Translation

2020-10-16 · Anonymous

In this paper, we propose a novel neural machine translation method that enables translation of multiple languages using a single universal model. Our approach introduces a small shared character space across languages a…

DecoderMachine TranslationTranslation

HierCode: A Lightweight Hierarchical Codebook for Zero-shot Chinese Text Recognition

2024-03-20 · Yuyi Zhang, Yuanzhi Zhu, Dezhi Peng, Peirong Zhang 외

Text recognition, especially for complex scripts like Chinese, faces unique challenges due to its intricate character structures and vast vocabulary. Traditional one-hot encoding methods struggle with the representation …

Zero-Shot Learning

Korean-to-Chinese Machine Translation using Chinese Character as Pivot Clue

2019-11-25 · Jeonghyeok Park, Hai Zhao

Korean-Chinese is a low resource language pair, but Korean and Chinese have a lot in common in terms of vocabulary. Sino-Korean words, which can be converted into corresponding Chinese characters, account for more than f…

Machine TranslationTranslation