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/LaraQianYang/Ouroboros
공식 코드Ouroboros: On Accelerating Training of Transformer-Based Language Models
https://github.com/LauraMartinus/ukuxhumana
공식 코드https://github.com/LeslieOverfitting/selective_distillation
공식 코드Selective Knowledge Distillation for Neural Machine Translation
https://github.com/LiberAI/NSpM
공식 코드Exploring Sequence-to-Sequence Models for SPARQL Pattern Composition
https://github.com/Lindsay125/gbpe
공식 코드Finding Better Subword Segmentation for Neural Machine Translation
https://github.com/LiqunChen0606/Graph-Optimal-Transport
공식 코드https://github.com/LiyuanLucasLiu/RAdam
공식 코드https://github.com/LiyuanLucasLiu/Transforemr-Clinic
공식 코드https://github.com/Lotemp/SarcasmSIGN
공식 코드Sarcasm SIGN: Interpreting Sarcasm with Sentiment Based Monolingual Machine Translation
https://github.com/M4t1ss/ConfidenceThroughAttention
공식 코드https://github.com/M4t1ss/MWE-Tools
공식 코드Paying Attention to Multi-Word Expressions in Neural Machine Translation
https://github.com/M4t1ss/SoftAlignments
공식 코드https://github.com/M4t1ss/parallel-corpora-tools
공식 코드https://github.com/MANGA-UOFA/M-DAT
공식 코드Multilingual Non-Autoregressive Machine Translation without Knowledge Distillation
https://github.com/MIR-MU/pine
공식 코드https://github.com/Machine-Learning-Tokyo/Poetry-GAN
공식 코드https://github.com/Maluuba/nlg-eval
공식 코드https://github.com/Mao-KU/JASS
공식 코드JASS: Japanese-specific Sequence to Sequence Pre-training for Neural Machine Translation
https://github.com/MarcoBerlot/Languages_for_Machine_Translation
공식 코드https://github.com/MarkPKCollier/MANNs4NMT
공식 코드https://github.com/McGill-NLP/latent-translation
공식 코드https://github.com/MeetKai/MK-SQuIT
공식 코드MK-SQuIT: Synthesizing Questions using Iterative Template-filling
https://github.com/MicrosoftTranslator/ToShipOrNotToShip
공식 코드To Ship or Not to Ship: An Extensive Evaluation of Automatic Metrics for Machine Translation
https://github.com/MinkaiXu/RSL-NMT
공식 코드Reciprocal Supervised Learning Improves Neural Machine Translation
https://github.com/Mlair77/nmt_adequacy
공식 코드Prevent the Language Model from being Overconfident in Neural Machine Translation
https://github.com/Moyu-42/Towards-A-Deep-Understanding-of-Multilingual-E2E-ST
공식 코드Towards a Deep Understanding of Multilingual End-to-End Speech Translation
https://github.com/MrShininnnnn/CECW
공식 코드https://github.com/Mukaffi28/Vashantor-A-Large-scale-Multilingual-Benchmark-Dataset
공식 코드https://github.com/MysteryVaibhav/robust_mtnt
공식 코드Improving Robustness of Machine Translation with Synthetic Noise
https://github.com/NJUNLP/MT-Patcher
공식 코드https://github.com/NLP-Playground/LaSS
공식 코드Learning Language Specific Sub-network for Multilingual Machine Translation
https://github.com/NLP2CT/Difficulty-Aware-MT-Evaluation
공식 코드https://github.com/NLP2CT/Meta-Curriculum
공식 코드Meta-Curriculum Learning for Domain Adaptation in Neural Machine Translation
https://github.com/NLP2CT/Unsupervised_Dialect_Translation
공식 코드Unsupervised Neural Dialect Translation with Commonality and Diversity Modeling
https://github.com/NLP2CT/norm-nmt
공식 코드Norm-Based Curriculum Learning for Neural Machine Translation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.