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/junjiehu/dali
Domain Adaptation of Neural Machine Translation by Lexicon Induction
https://github.com/junnyu/paddle_t5
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
https://github.com/jwieting/beyond-bleu
Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
https://github.com/jxz542189/TCN_classification
An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
https://github.com/k-randl/self-explaining_llms
https://github.com/kaituoxu/Speech-Transformer
https://github.com/kaituoxu/SpeechTransformer
https://github.com/kaleidophon/nlp-uncertainty-zoo
Wat zei je? Detecting Out-of-Distribution Translations with Variational Transformers
https://github.com/kaletap/language-style-transfer-pytorch
https://github.com/kaletap/nlp-experiments
A Probabilistic Formulation of Unsupervised Text Style Transfer
https://github.com/kaletap/nlp-style-transfer
https://github.com/karanthakkar97/Text-summarization-with-Seq2Seq
https://github.com/karenacorn99/explore-bert
https://github.com/karlie38/torchstudy
https://github.com/karpathy/build-nanogpt
https://github.com/karpathy/llm.c
https://github.com/karpathy/makemore
On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
https://github.com/karpathy/minGPT
https://github.com/karpathy/minbpe
https://github.com/karta282950/bert-multiclass
https://github.com/keiyamashita111/aaproject
https://github.com/kelly2016/multi-label-bert
https://github.com/keonlee9420/Parallel-Tacotron2
https://github.com/keonlee9420/Stepwise_Monotonic_Multihead_Attention
Online and Linear-Time Attention by Enforcing Monotonic Alignments
https://github.com/keonlee9420/VAENAR-TTS
FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow
https://github.com/keshavganapathy/genetic-algorithm-jhu
https://github.com/kevinduh/san_mrc
Multi-task Learning with Sample Re-weighting for Machine Reading Comprehension
https://github.com/kevinlu1248/pyate
ATR4S: Toolkit with State-of-the-art Automatic Terms Recognition Methods in Scala
https://github.com/keyonvafa/career-code
https://github.com/kh-kim/simple-nmt
Effective Approaches to Attention-based Neural Machine Translation
https://github.com/kh-mo/QA_wikisql
https://github.com/kheeong/XLM_OWN
https://github.com/khushsi/Finetuning_BART_for_FACET_Summarization
https://github.com/khwajawisal/Attention-augmented-Convolutional-Neural-Networks
https://github.com/kiko441500/google_bert
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.