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/tanggongbo/normalization-NMT
공식 코드An Evaluation of Neural Machine Translation Models on Historical Spelling Normalization
https://github.com/tartunlp/inherent-domains-wmt21
공식 코드https://github.com/tatHi/optok
공식 코드https://github.com/tatHi/optok4at
공식 코드https://github.com/tathi/maxmatch_dropout
공식 코드https://github.com/teelinsan/parallel-decoding
공식 코드Accelerating Transformer Inference for Translation via Parallel Decoding
https://github.com/tempra28/nmtrnng
공식 코드Learning to Parse and Translate Improves Neural Machine Translation
https://github.com/tempra28/tree2seq
공식 코드https://github.com/temu-bsc/seq-to-seq-catalan
공식 코드https://github.com/tencent-ailab/ICML21_OAXE
공식 코드Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation
https://github.com/tensorflow/lingvo
공식 코드The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation
https://github.com/tensorflow/models
공식 코드https://github.com/tensorflow/tensor2tensor
공식 코드Depthwise Separable Convolutions for Neural Machine Translation
https://github.com/terryyz/ice-score
공식 코드ICE-Score: Instructing Large Language Models to Evaluate Code
https://github.com/terryyz/llm-code-eval
공식 코드ICE-Score: Instructing Large Language Models to Evaluate Code
https://github.com/terryyz/rtt-rethinking
공식 코드Rethinking Round-Trip Translation for Machine Translation Evaluation
https://github.com/teslacool/SCA
공식 코드Soft Contextual Data Augmentation for Neural Machine Translation
https://github.com/text-machine-lab/HierarchicalTransformer
공식 코드https://github.com/textshuttle/exploiting-bias-to-debias
공식 코드Exploiting Biased Models to De-bias Text: A Gender-Fair Rewriting Model
https://github.com/thammegowda/005-nmt-imbalance
공식 코드Finding the Optimal Vocabulary Size for Neural Machine Translation
https://github.com/thammegowda/006-many-to-eng
공식 코드Many-to-English Machine Translation Tools, Data, and Pretrained Models
https://github.com/thammegowda/007-mt-eval-macro
공식 코드https://github.com/tharindudr/transQuest
공식 코드https://github.com/thespectrewithin/joint-align
공식 코드Cross-lingual Alignment vs Joint Training: A Comparative Study and A Simple Unified Framework
https://github.com/thinkwee/DPP_CNN_Summarization
공식 코드https://github.com/thompsonb/prism
공식 코드Automatic Machine Translation Evaluation in Many Languages via Zero-Shot Paraphrasing
https://github.com/thu-coai/da-transformer
공식 코드Directed Acyclic Transformer for Non-Autoregressive Machine Translation
https://github.com/thunlp-mt/ckd
공식 코드Continual Knowledge Distillation for Neural Machine Translation
https://github.com/thunlp-mt/plm4mt
공식 코드MSP: Multi-Stage Prompting for Making Pre-trained Language Models Better Translators
https://github.com/thunlp-mt/promptgating4mctg
공식 코드An Extensible Plug-and-Play Method for Multi-Aspect Controllable Text Generation
https://github.com/thunlp-mt/template-nmt
공식 코드A Template-based Method for Constrained Neural Machine Translation
https://github.com/thunlp-mt/transformer-dmb
공식 코드Dynamic Multi-Branch Layers for On-Device Neural Machine Translation
https://github.com/thunlp/subchartokenization
공식 코드Sub-Character Tokenization for Chinese Pretrained Language Models
https://github.com/tienthanhdhcn/VnAPE
공식 코드https://github.com/tilde-nlp/terminology_translation
공식 코드Facilitating Terminology Translation with Target Lemma Annotations
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.