paper-with-me

Papers

Neural Machine Translation of Rare Words with Subword Units

2015-08-31 · ACL 2016 8 · Rico Sennrich, Barry Haddow, Alexandra Birch

Neural machine translation (NMT) models typically operate with a fixed vocabulary, but translation is an open-vocabulary problem. Previous work addresses the translation of out-of-vocabulary words by backing off to a dictionary. In this paper, we introduce a simpler and more effective approach, making the NMT model capable of open-vocabulary translation by encoding rare and unknown words as sequences of subword units. This is based on the intuition that various word classes are translatable via smaller units than words, for instance names (via character copying or transliteration), compounds (via compositional translation), and cognates and loanwords (via phonological and morphological transformations). We discuss the suitability of different word segmentation techniques, including simple character n-gram models and a segmentation based on the byte pair encoding compression algorithm, and empirically show that subword models improve over a back-off dictionary baseline for the WMT 15 translation tasks English-German and English-Russian by 1.1 and 1.3 BLEU, respectively.

📄 PDF Abstract BibTeX arXiv:1508.07909

Code (26)

rsennrich/subword-nmt 공식 구현
Automattic/wp-translate tf
Avmb/code-docstring-corpus
EdinburghNLP/code-docstring-corpus
HarshKhandelwal1552/Language_classifier_with_Naive_Bayes
PaulSudarshan/Language-Classification-Using-Naive-Bayes-Algorithm
SeonbeomKim/Python-Bype_Pair_Encoding
SeonbeomKim/Python-Byte_Pair_Encoding
ThAIKeras/bert tf
VKCOM/YouTokenToMe
Xinsen-Zhang/transformer paddle
facebookresearch/fairseq pytorch
glample/fastBPE
google/sentencepiece tf
johnr0/TaleBrush-backend pytorch
karpathy/minbpe
kh-mo/QA_wikisql
ksulima/Unsupervised-method-to-NPL-Polish-language
lkfo415579/MT-Readling-List tf
nyu-dl/dl4mt-c2c
nyu-dl/dl4mt-cdec
nyu-dl/dl4mt-simul-trans
salesforce/GeDi pytorch
simonjisu/NMT pytorch
siyuofzhou/CNNSeqToSeq torch
thinkwee/DPP_CNN_Summarization pytorch

Tasks

Machine TranslationNMTSegmentationTranslation

Methods 이 논문이 사용한 방법론

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

Optimizing Segmentation Granularity for Neural Machine Translation

2018-10-19 · Elizabeth Salesky, Andrew Runge, Alex Coda, Jan Niehues 외

In neural machine translation (NMT), it is has become standard to translate using subword units to allow for an open vocabulary and improve accuracy on infrequent words. Byte-pair encoding (BPE) and its variants are the …

Machine TranslationNMTTranslation

Finding Better Subword Segmentation for Neural Machine Translation

2018-07-25 · Yingting Wu, Hai Zhao

For different language pairs, word-level neural machine translation (NMT) models with a fixed-size vocabulary suffer from the same problem of representing out-of-vocabulary (OOV) words. The common practice usually replac…

Machine TranslationNMTSegmentationTranslation

Modeling Multi-granularity Segmentation for Rare Words in Neural Machine Translation

2021-09-17 · ACL ARR September 2021 9 · Anonymous

Segmenting rare words into subwords has become a commonly used and effective way to alleviate the open vocabulary problem in Neural Machine Translation (NMT). The existing dominant segmentation methods either give rare w…

DiversityMachine TranslationNMTSegmentation+1

Multitask Learning For Different Subword Segmentations In Neural Machine Translation

2019-10-27 · EMNLP (IWSLT) 2019 11 · Tejas Srinivasan, Ramon Sanabria, Florian Metze

In Neural Machine Translation (NMT) the usage of subwords and characters as source and target units offers a simple and flexible solution for translation of rare and unseen words. However, selecting the optimal subword s…

DecoderMachine TranslationNMTSegmentation+1

An Analysis of BPE Vocabulary Trimming in Neural Machine Translation

2024-03-30 · Marco Cognetta, Tatsuya Hiraoka, Naoaki Okazaki, Rico Sennrich 외

We explore threshold vocabulary trimming in Byte-Pair Encoding subword tokenization, a postprocessing step that replaces rare subwords with their component subwords. The technique is available in popular tokenization lib…

Machine TranslationTranslation