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/Saurav0074/nmt-based-word-transduction
공식 코드https://github.com/ShannonAI/backdoor_nlg
공식 코드Defending Against Backdoor Attacks in Natural Language Generation
https://github.com/ShannonAI/fast-knn-nmt
공식 코드https://github.com/ShannonAI/glyce
공식 코드https://github.com/SimiaoZuo/Caching-Adv
공식 코드ARCH: Efficient Adversarial Regularized Training with Caching
https://github.com/SimiaoZuo/Stackelberg-Adv
공식 코드Adversarial Regularization as Stackelberg Game: An Unrolled Optimization Approach
https://github.com/Simpleple/Verdi
공식 코드Verdi: Quality Estimation and Error Detection for Bilingual Corpora
https://github.com/Smu-Tan/Remedy
공식 코드Remedy: Learning Machine Translation Evaluation from Human Preferences with Reward Modeling
https://github.com/Smu-Tan/ZS-NMT-Variations
공식 코드Towards a Better Understanding of Variations in Zero-Shot Neural Machine Translation Performance
https://github.com/SouravDutta91/map-low-resource-embeddings
공식 코드Mapping Supervised Bilingual Word Embeddings from English to low-resource languages
https://github.com/StatNLP/mt-correct-mark-interface
공식 코드Correct Me If You Can: Learning from Error Corrections and Markings
https://github.com/StillKeepTry/ECM-NMT
공식 코드https://github.com/Styrke/master-code
공식 코드Neural Machine Translation with Characters and Hierarchical Encoding
https://github.com/SunbowLiu/CopyingPenalty
공식 코드On the Copying Behaviors of Pre-Training for Neural Machine Translation
https://github.com/SunbowLiu/SurfaceFusion
공식 코드Understanding and Improving Encoder Layer Fusion in Sequence-to-Sequence Learning
https://github.com/SwordYork/DCNMT
공식 코드https://github.com/THUNLP-MT/L2Copy4APE
공식 코드https://github.com/THUNLP-MT/Mask-Align
공식 코드https://github.com/THUNLP-MT/THUMT
공식 코드https://github.com/THUNLP-MT/TRICE
공식 코드Transfer Learning for Sequence Generation: from Single-source to Multi-source
https://github.com/THUNLP-MT/UCE4BT
공식 코드Improving Back-Translation with Uncertainty-based Confidence Estimation
https://github.com/THUNLP-MT/Voting4SC
공식 코드Modeling Voting for System Combination in Machine Translation
https://github.com/TIXFeniks/neurips2019_intrus
공식 코드https://github.com/Tiiiger/bert_score
공식 코드https://github.com/Toadoum/Ngambay-French-Neural-Machine-Translation-sba_fr_v1-
공식 코드https://github.com/UBC-NLP/africaNLP2021
공식 코드Translating the Unseen? Yoruba-English MT in Low-Resource, Morphologically-Unmarked Settings
https://github.com/UKPLab/coling2018-xling_argument_mining
공식 코드Cross-lingual Argumentation Mining: Machine Translation (and a bit of Projection) is All You Need!
https://github.com/UmerTariq1/Urdu_MsMarco_Translation_Retrieval
공식 코드Enabling Low-Resource Language Retrieval: Establishing Baselines for Urdu MS MARCO
https://github.com/Unbabel/COMET
공식 코드https://github.com/UriSha/EmbeddinglessNMT
공식 코드https://github.com/Usprogis/Latvian-Twitter-Eater-Corpus
공식 코드https://github.com/UtsaChattopadhyay/MSAI/blob/main/SourceCode%20for%20low%20Resource%20MT.zip
공식 코드https://github.com/VProv/BPE-Dropout
공식 코드https://github.com/Veteranback/miniformer
공식 코드Efficient Machine Translation with a BiLSTM-Attention Approach
https://github.com/VisualJoyce/andushu
공식 코드Investigating Math Word Problems using Pretrained Multilingual Language Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.