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/jiacheng-xu/text-sum-uncertainty
https://github.com/jiahuei/Self-Critical-SCST-TensorFlow
https://github.com/jiajun169/mindspore_models/tree/main/Unet3d
3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation
https://github.com/jiajunhua/facebookresearch-MUSE
Exploiting Similarities among Languages for Machine Translation
https://github.com/jiali-ms/JLM
Strategies for Training Large Vocabulary Neural Language Models
https://github.com/jiangnanhugo/seq2seq_cuda
Neural Machine Translation by Jointly Learning to Align and Translate
https://github.com/jiaruncao/BioCopyMechanism
MASS: Masked Sequence to Sequence Pre-training for Language Generation
https://github.com/jim-schwoebel/allie
https://github.com/jincan333/lot
https://github.com/jinjiren/recurrent-image-annotator-web-demo
Annotation Order Matters: Recurrent Image Annotator for Arbitrary Length Image Tagging
https://github.com/jinliangwei/tensor2tensor-1.11
https://github.com/jinzhenfan/BERT
https://github.com/jishavm/TextStyleTransfer
https://github.com/jklafka/noisy-nets
https://github.com/jlibovicky/char-nmt-fairseq
https://github.com/jlrussin/syntactic_attention
Compositional generalization in a deep seq2seq model by separating syntax and semantics
https://github.com/jmcrego/bisync
Bilingual Synchronization: Restoring Translational Relationships with Editing Operations
https://github.com/jmnolte/hccnet
https://github.com/jmyrberg/finnlem
Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
https://github.com/joebluems/Soul_Of_AI
https://github.com/john-bradshaw/rxn-lm
https://github.com/johngull/gradinit
GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training
https://github.com/johnr0/TaleBrush-backend
https://github.com/jonas-becker/text-generation
https://github.com/jongwooko/nash-pruning-official
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
https://github.com/joongbo/tta
https://github.com/josephch405/curriculum-nmt
Improving Neural Machine Translation Models with Monolingual Data
https://github.com/joytianya/google_bert
https://github.com/jpark621/language-style-transfer
https://github.com/jsuarez5341/Efficient-Dynamic-Batching
Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
https://github.com/juletx/lm-evaluation-harness
https://github.com/juliakreutzer/bandit-neuralmonkey
Bandit Structured Prediction for Neural Sequence-to-Sequence Learning
https://github.com/jungokasai/XOR_QA_MTPipeline
https://github.com/jungokasai/t2r
Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models
https://github.com/junhahyung/bert_finetune
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.