https://github.com/zdou0830/DDA
공식 코드Domain Differential Adaptation for Neural Machine Translation
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/zdou0830/crosslingual_summarization_semantic
공식 코드https://github.com/zdou0830/dynamic_select_weight
공식 코드Dynamic Data Selection and Weighting for Iterative Back-Translation
https://github.com/zeecoder606/PF-Adaptation
공식 코드https://github.com/zerocstaker/constrained_ape
공식 코드Incorporating Terminology Constraints in Automatic Post-Editing
https://github.com/zhajiahe/Token_Drop
공식 코드https://github.com/zhangr2021/TransProQA
공식 코드https://github.com/zhangr2021/litmt_eval
공식 코드https://github.com/zhanjiaao/nat_depa
공식 코드DePA: Improving Non-autoregressive Machine Translation with Dependency-Aware Decoder
https://github.com/zhaofengwu/rfa-doc-mt
공식 코드Modeling Context With Linear Attention for Scalable Document-Level Translation
https://github.com/zhaoyiran924/adv-in-context-learning
공식 코드https://github.com/zhawe01/fairseq-gec
공식 코드https://github.com/zhengkid/eit-enhanced-interactive-transformer
공식 코드https://github.com/zhengkid/partialformer
공식 코드PartialFormer: Modeling Part Instead of Whole for Machine Translation
https://github.com/zhenglisec/Blind-Watermark-for-DNN
공식 코드https://github.com/zhengliz/natural-adversary
공식 코드https://github.com/zhengxxn/adaptive-knn-mt
공식 코드https://github.com/zhengxxn/uda-knn
공식 코드Non-Parametric Unsupervised Domain Adaptation for Neural Machine Translation
https://github.com/zhengzx-nlp/dynamic-nmt
공식 코드https://github.com/zhengzx-nlp/past-and-future-nmt
공식 코드https://github.com/zhengzx-nlp/reder
공식 코드Duplex Sequence-to-Sequence Learning for Reversible Machine Translation
https://github.com/zhenyangiacas/hjqe
공식 코드Rethink about the Word-level Quality Estimation for Machine Translation from Human Judgement
https://github.com/zhenyangiacas/wets
공식 코드https://github.com/zhewei-sun/slanginterp
공식 코드https://github.com/zhiqu22/PhasedDecoder
공식 코드https://github.com/zhiqu22/ZeroTrans
공식 코드https://github.com/zhiqu22/adapnoncenter
공식 코드Adapting to Non-Centered Languages for Zero-shot Multilingual Translation
https://github.com/zhiqu22/mitre
공식 코드Registering Source Tokens to Target Language Spaces in Multilingual Neural Machine Translation
https://github.com/zhjgao/difformer
공식 코드Empowering Diffusion Models on the Embedding Space for Text Generation
https://github.com/zhongmz/SiMT-Hallucination
공식 코드https://github.com/zhongmz/contextconsistencybitraining4simt
공식 코드Context Consistency between Training and Testing in Simultaneous Machine Translation
https://github.com/zhongxingyu/seer
공식 코드Learning the Relation between Code Features and Code Transforms with Structured Prediction
https://github.com/zhougroup/BAM
공식 코드https://github.com/zhouh/chunk-nmt
공식 코드https://github.com/zhouyuxuanyx/multimax
공식 코드https://github.com/zhuchen03/gradinit
공식 코드GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.