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/baoguangsheng/g-transformer
공식 코드https://github.com/baoguangsheng/nat-on-doc
공식 코드https://github.com/baoguangsheng/target-side-augmentation
공식 코드Target-Side Augmentation for Document-Level Machine Translation
https://github.com/baohaoliao/multiback
공식 코드Back-translation for Large-Scale Multilingual Machine Translation
https://github.com/baosongyang/WRD
공식 코드Assessing the Ability of Self-Attention Networks to Learn Word Order
https://github.com/baoy-nlp/CNAT
공식 코드Non-Autoregressive Translation by Learning Target Categorical Codes
https://github.com/baudzhou/wyweb
공식 코드https://github.com/bbrimacombe/quick-back-translation
공식 코드https://github.com/bcmi220/esc4nmt
공식 코드Explicit Sentence Compression for Neural Machine Translation
https://github.com/bcmi220/runmt
공식 코드Reference Language based Unsupervised Neural Machine Translation
https://github.com/bdusell/stack-attention
공식 코드Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns
https://github.com/beckdaniel/acl2018_graph2seq
공식 코드Graph-to-Sequence Learning using Gated Graph Neural Networks
https://github.com/benjamin-marie/meta_evaluation_mt
공식 코드Scientific Credibility of Machine Translation Research: A Meta-Evaluation of 769 Papers
https://github.com/berkeley-nlp/lex-rules
공식 코드Using Language Models to Disambiguate Lexical Choices in Translation
https://github.com/berlino/btg-seq2seq
공식 코드https://github.com/berlino/tensor2struct-public
공식 코드Structured Reordering for Modeling Latent Alignments in Sequence Transduction
https://github.com/bert-nmt/bert-nmt
공식 코드https://github.com/bghojogh/Pixel-Aligned-Face-Recognition
공식 코드Pixel-Level Alignment of Facial Images for High Accuracy Recognition Using Ensemble of Patches
https://github.com/bhaddow/hume-emnlp16
공식 코드https://github.com/bhaddow/pmindia-crawler
공식 코드PMIndia -- A Collection of Parallel Corpora of Languages of India
https://github.com/biaofuxmu/conslt
공식 코드A Token-level Contrastive Framework for Sign Language Translation
https://github.com/biaofuxmu/east
공식 코드LLMs Can Achieve High-quality Simultaneous Machine Translation as Efficiently as Offline
https://github.com/biblenlp/ebible-experiments
공식 코드The eBible Corpus: Data and Model Benchmarks for Bible Translation for Low-Resource Languages
https://github.com/bigganbing/Fairseq_MorphTE
공식 코드https://github.com/billptw/fasttrees
공식 코드FastTrees: Parallel Latent Tree-Induction for Faster Sequence Encoding
https://github.com/bingcongli/vasso
공식 코드Enhancing Sharpness-Aware Optimization Through Variance Suppression
https://github.com/bithlp/debackx
공식 코드Exploring In-Image Machine Translation with Real-World Background
https://github.com/blcuicall/mcts
공식 코드https://github.com/bltlab/paranames
공식 코드https://github.com/boknilev/nmt-repr-analysis
공식 코드What do Neural Machine Translation Models Learn about Morphology?
https://github.com/bonaventuredossou/ffr-v1
공식 코드https://github.com/bonaventuredossou/fonasr
공식 코드https://github.com/borgr/auto_challenge_sets
공식 코드Automatically Extracting Challenge Sets for Non local Phenomena in Neural Machine Translation
https://github.com/borgr/nematus
공식 코드Enhancing the Transformer Decoder with Transition-based Syntax
https://github.com/boun-tabi/NLI-TR
공식 코드Data and Representation for Turkish Natural Language Inference
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.