https://github.com/Waino/OpenNMT-py
공식 코드Transfer learning and subword sampling for asymmetric-resource one-to-many neural 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/Waino/morfessor-emprune
공식 코드Morfessor EM+Prune: Improved Subword Segmentation with Expectation Maximization and Pruning
https://github.com/WorldHellow/mHallucinations-LLM
공식 코드https://github.com/WulffHunter/log_generator
공식 코드https://github.com/X-LANCE/SLAM-LLM
공식 코드SLAM-AAC: Enhancing Audio Captioning with Paraphrasing Augmentation and CLAP-Refine through LLMs
https://github.com/XL2248/CPCC
공식 코드Modeling Bilingual Conversational Characteristics for Neural Chat Translation
https://github.com/XapaJIaMnu/marian-dev
공식 코드Not all parameters are born equal: Attention is mostly what you need
https://github.com/XudongLinthu/context-gated-convolution
공식 코드https://github.com/XuezheMax/fairseq-apollo
공식 코드https://github.com/XuezheMax/flowseq
공식 코드FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow
https://github.com/Yorko/gender-unbiased_BERT-based_pronoun_resolution
공식 코드https://github.com/YuchenJin/autolrs
공식 코드AutoLRS: Automatic Learning-Rate Schedule by Bayesian Optimization on the Fly
https://github.com/Yusser96/Exploring-Paracrawl-for-Document-level-Neural-Machine-Translation
공식 코드Exploring Paracrawl for Document-level Neural Machine Translation
https://github.com/YuweiYin/CROP
공식 코드https://github.com/YuweiYin/GTrans
공식 코드GTrans: Grouping and Fusing Transformer Layers for Neural Machine Translation
https://github.com/YuweiYin/HLT-MT
공식 코드HLT-MT: High-resource Language-specific Training for Multilingual Neural Machine Translation
https://github.com/YuweiYin/UM4
공식 코드https://github.com/ZNLP/SOTA-MT
공식 코드https://github.com/ZNLP/sb-nmt
공식 코드Synchronous Bidirectional Inference for Neural Sequence Generation
https://github.com/ZhangShiyue/ChrEn
공식 코드ChrEn: Cherokee-English Machine Translation for Endangered Language Revitalization
https://github.com/ZhangShiyue/ChrEnTranslate
공식 코드https://github.com/ZhenYangIACAS/NMT_GAN
공식 코드Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets
https://github.com/ZhenYangIACAS/unsupervised-NMT
공식 코드https://github.com/ZurichNLP/ContraPro
공식 코드https://github.com/ZurichNLP/domain-robustness
공식 코드https://github.com/ZurichNLP/monotonicity_loss
공식 코드https://github.com/ZurichNLP/mt-parity-assessment-data
공식 코드A Set of Recommendations for Assessing Human-Machine Parity in Language Translation
https://github.com/ZurichNLP/multiturn-llm-docmt
공식 코드Source-primed Multi-turn Conversation Helps Large Language Models Translate Documents
https://github.com/ZurichNLP/sockeye
공식 코드https://github.com/ZurichNLP/understanding-mbr
공식 코드Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translation
https://github.com/aalto-speech/dbca
공식 코드https://github.com/abhishekbamotra/transdocs
공식 코드TransDocs: Optical Character Recognition with word to word translation
https://github.com/abjadai/catt
공식 코드https://github.com/acerkoo/lcs
공식 코드LCS: A Language Converter Strategy for Zero-Shot Neural Machine Translation
https://github.com/acolas1/GAP_COLING2022
공식 코드GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text Generation
https://github.com/adaptnmt/adaptmllm
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.