https://github.com/zhuchen03/maxva
공식 코드MaxVA: Fast Adaptation of Step Sizes by Maximizing Observed Variance of Gradients
Papers with Code 아카이브
Machine Translation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 10
- 평가표
- 84
- 보존된 평가 기록
- 438
Machine translation is the task of translating a sentence in a source language to a different target language.
Approaches for machine translation can range from rule-based to statistical to neural-based. More recently, encoder-decoder attention-based architectures like BERT have attained major improvements in machine translation.
One of the most popular datasets used to benchmark machine translation systems is the WMT family of datasets. Some of the most commonly used evaluation metrics for machine translation systems include BLEU, METEOR, NIST, and others.
<span style="color:grey; opacity: 0.6">( Image credit: Google seq2seq )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/zhuohan123/hint-nart
공식 코드Hint-Based Training for Non-Autoregressive Machine Translation
https://github.com/zippotju/Exposure-Bias-Hallucination-Domain-Shift
공식 코드On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translation
https://github.com/ziwang-klvk/cfq-rbmt
공식 코드On Evaluating Multilingual Compositional Generalization with Translated Datasets
https://github.com/zjpbinary/CSCBLI
공식 코드Combining Static Word Embeddings and Contextual Representations for Bilingual Lexicon Induction
https://github.com/zjwang21/strokenet
공식 코드https://github.com/zlinao/Variational-Transformer
공식 코드https://github.com/znlp/bigtrans
공식 코드https://github.com/znlp/bigtranslate
공식 코드https://github.com/znlp/zero-shot-st
공식 코드Discrete Cross-Modal Alignment Enables Zero-Shot Speech Translation
https://github.com/zomux/lanmt
공식 코드https://github.com/zomux/lanmt-ebm
공식 코드Iterative Refinement in the Continuous Space for Non-Autoregressive Neural Machine Translation
https://github.com/zomux/nmtdec
공식 코드https://github.com/zorikg/KoBE
공식 코드https://github.com/zouharvi/COMET-early-exit
공식 코드Early-Exit and Instant Confidence Translation Quality Estimation
https://github.com/zouharvi/LeverageAlign
공식 코드https://github.com/zouharvi/mt-metric-estimation
공식 코드Poor Man's Quality Estimation: Predicting Reference-Based MT Metrics Without the Reference
https://github.com/zouharvi/ptakopet
공식 코드Backtranslation Feedback Improves User Confidence in MT, Not Quality
https://github.com/zouharvi/reference-mt-distill
공식 코드Sampling and Filtering of Neural Machine Translation Distillation Data
https://github.com/zouharvi/subset2evaluate
공식 코드How to Select Datapoints for Efficient Human Evaluation of NLG Models?
https://github.com/zouharvi/tokenization-scorer
공식 코드https://github.com/zouharvi/vocab-stealing
공식 코드Stolen Subwords: Importance of Vocabularies for Machine Translation Model Stealing
https://github.com/zurichnlp/contradecode
공식 코드https://github.com/zurichnlp/coverage-contrastive-conditioning
공식 코드https://github.com/zurichnlp/mbr-sensitivity
공식 코드https://github.com/zurichnlp/multipivotnmt
공식 코드Investigating Multi-Pivot Ensembling with Massively Multilingual Machine Translation Models
https://github.com/zurichnlp/nmtscore
공식 코드NMTScore: A Multilingual Analysis of Translation-based Text Similarity Measures
https://github.com/zurichnlp/segtest
공식 코드How Suitable Are Subword Segmentation Strategies for Translating Non-Concatenative Morphology?
https://github.com/zurichnlp/spoken-to-signed-translation
공식 코드An Open-Source Gloss-Based Baseline for Spoken to Signed Language Translation
https://github.com/zurichnlp/translation-direction-detection
공식 코드Machine Translation Models are Zero-Shot Detectors of Translation Direction
https://github.com/zwhe99/MAPS-mt
공식 코드Exploring Human-Like Translation Strategy with Large Language Models
https://github.com/zwhe99/feedbackmt
공식 코드https://github.com/zwhe99/selftraining4unmt
공식 코드Bridging the Data Gap between Training and Inference for Unsupervised Neural Machine Translation
https://github.com/zzsfornlp/znmt-merge
공식 코드Exploring Recombination for Efficient Decoding of Neural Machine Translation
https://gitlab.com/farid-fari/fewshot-learning
공식 코드https://gitlab.com/mzboito/attention_study
공식 코드Empirical Evaluation of Sequence-to-Sequence Models for Word Discovery in Low-resource Settings
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.