https://github.com/marziehf/variation-generation
공식 코드The Unreasonable Volatility of Neural Machine Translation Models
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/masakhane-io/afridoc-mt
공식 코드https://github.com/masakhane-io/masakhane-mt
공식 코드Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages
https://github.com/masakhane-io/masakhane-news
공식 코드MasakhaNEWS: News Topic Classification for African languages
https://github.com/masoudjs/simalign
공식 코드https://github.com/massabaali7/speech_parallel_corpus
공식 코드https://github.com/matejulcar/slot5-tools
공식 코드Sequence to sequence pretraining for a less-resourced Slovenian language
https://github.com/matthieufp/commute
공식 코드Tackling Ambiguity with Images: Improved Multimodal Machine Translation and Contrastive Evaluation
https://github.com/matthieufp/vgamt
공식 코드Tackling Ambiguity with Images: Improved Multimodal Machine Translation and Contrastive Evaluation
https://github.com/matthieufp/zerommt
공식 코드https://github.com/mattiadg/SR-NMT
공식 코드https://github.com/maxattezekbayev/alpha-relu
공식 코드https://github.com/maxwell1447/fairseq
공식 코드Towards Example-Based NMT with Multi-Levenshtein Transformers
https://github.com/maxylee/3am
공식 코드3AM: An Ambiguity-Aware Multi-Modal Machine Translation Dataset
https://github.com/mccaffary/continual-learning
공식 코드https://github.com/mcgill-nlp/naija-representation-in-llms
공식 코드https://github.com/meganndare/cantonese-nlp
공식 코드https://github.com/megvii-research/Arch-Net
공식 코드Arch-Net: Model Distillation for Architecture Agnostic Model Deployment
https://github.com/meinwerk/WordPrediction
공식 코드https://github.com/melkor169/LeadSheetGen_Valence
공식 코드Generating Lead Sheets with Affect: A Novel Conditional seq2seq Framework
https://github.com/meta-inf/suq-nlg
공식 코드On Subjective Uncertainty Quantification and Calibration in Natural Language Generation
https://github.com/meta-metrics/metametrics
공식 코드MetaMetrics-MT: Tuning Meta-Metrics for Machine Translation via Human Preference Calibration
https://github.com/mgaido91/FBK-fairseq-ST
공식 코드https://github.com/mgheini/xattn-transfer-for-mt
공식 코드Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translation
https://github.com/michaelrzhang/lookahead
공식 코드https://github.com/michellekappl/mt_gender_german
공식 코드https://github.com/michiyasunaga/bifi
공식 코드https://github.com/microsoft/DeepSpeed
공식 코드Scalable and Efficient MoE Training for Multitask Multilingual Models
https://github.com/microsoft/Lightweight-Low-Resource-NMT
공식 코드https://github.com/microsoft/MASS
공식 코드MASS: Masked Sequence to Sequence Pre-training for Language Generation
https://github.com/microsoft/NeuralSpeech
공식 코드FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition
https://github.com/microsoft/ProphetNet
공식 코드AR-Diffusion: Auto-Regressive Diffusion Model for Text Generation
https://github.com/microsoft/automoe
공식 코드https://github.com/microsoft/gpt-mt
공식 코드How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation
https://github.com/microsoft/inmt-lite
공식 코드https://github.com/microsoft/promptbench
공식 코드PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.