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/microsoft/reina
공식 코드https://github.com/microsoft/residual
공식 코드https://github.com/microsoft/stochastic-mixture-of-experts
공식 코드Taming Sparsely Activated Transformer with Stochastic Experts
https://github.com/microsoft/torchscale
공식 코드https://github.com/microsoft/unilm
공식 코드EdgeFormer: A Parameter-Efficient Transformer for On-Device Seq2seq Generation
https://github.com/microsoft/unilm/tree/master/deltalm
공식 코드https://github.com/microsoft/vert-papers/tree/master/papers/AdvPicker
공식 코드AdvPicker: Effectively Leveraging Unlabeled Data via Adversarial Discriminator for Cross-Lingual NER
https://github.com/microsofttranslator/gate
공식 코드GATE: A Challenge Set for Gender-Ambiguous Translation Examples
https://github.com/microsofttranslator/ntrex
공식 코드A Benchmark for Evaluating Machine Translation Metrics on Dialects Without Standard Orthography
https://github.com/middlekisser/GMNMT
공식 코드A Novel Graph-based Multi-modal Fusion Encoder for Neural Machine Translation
https://github.com/midobal/OpenNMT-py
공식 코드Demonstration of a Neural Machine Translation System with Online Learning for Translators
https://github.com/midobal/mthd
공식 코드Two Demonstrations of the Machine Translation Applications to Historical Documents
https://github.com/migalkin/SQuAD-es-mt
공식 코드El Departamento de Nosotros: How Machine Translated Corpora Affects Language Models in MRC Tasks
https://github.com/mikahama/natas
공식 코드https://github.com/milanlproc/interpretability-mt-gender-bias
공식 코드https://github.com/mindspore-lab/models
공식 코드Efficient Machine Translation with a BiLSTM-Attention Approach
https://github.com/mingdachen/mVGVAE
공식 코드Exemplar-Controllable Paraphrasing and Translation using Bitext
https://github.com/minghao-wu/transagents
공식 코드https://github.com/mingjund/mapudungun-corpus
공식 코드https://github.com/mingzi151/ahc-si
공식 코드NAIST-SIC-Aligned: an Aligned English-Japanese Simultaneous Interpretation Corpus
https://github.com/mingzi151/interpretationdata
공식 코드It is Not as Good as You Think! Evaluating Simultaneous Machine Translation on Interpretation Data
https://github.com/mingzi151/spokenvocab
공식 코드Generating Synthetic Speech from SpokenVocab for Speech Translation
https://github.com/minwhoo/gacl
공식 코드https://github.com/mipunivie/deeperwin
공식 코드https://github.com/mir-mu/regemt
공식 코드Regressive Ensemble for Machine Translation Quality Evaluation
https://github.com/mir-mu/softalign_objectives
공식 코드Soft Alignment Objectives for Robust Adaptation of Language Generation
https://github.com/mit-han-lab/hardware-aware-transformers
공식 코드HAT: Hardware-Aware Transformers for Efficient Natural Language Processing
https://github.com/mit-han-lab/lite-transformer
공식 코드https://github.com/mitramir55/prose2poem
공식 코드Prose2Poem: The Blessing of Transformers in Translating Prose to Persian Poetry
https://github.com/mitvis/vistext
공식 코드https://github.com/mjlaali/ConcoLeDisCo
공식 코드Automatic Mapping of French Discourse Connectives to PDTB Discourse Relations
https://github.com/ml-jku/hopfield-layers
공식 코드https://github.com/mmarmonier/SWELLS
공식 코드https://github.com/moore3930/beyondsharedvocabulary
공식 코드https://github.com/moore3930/calibrating-llm-mt
공식 코드Calibrating Translation Decoding with Quality Estimation on LLMs
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.