Papers with Code 아카이브
NMT
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 0
- 보존된 평가 기록
- 0
Neural machine translation is an approach to machine translation that uses an artificial neural network to predict the likelihood of a sequence of words, typically modeling entire sentences in a single integrated model.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/conceptofmind/lamda-rlhf-pytorch
https://github.com/cordercorder/knn-models
https://github.com/cui0523/Code6/tree/main/gnmt_v2
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
https://github.com/dalek7/attention
Effective Approaches to Attention-based Neural Machine Translation
https://github.com/danielinux7/Multilingual-Parallel-Corpus
Towards Reasonably-Sized Character-Level Transformer NMT by Finetuning Subword Systems
https://github.com/dannigt/kit-iwslt2023-multilingual
https://github.com/davidsvaughn/dts-tf
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
https://github.com/deep-spin/OpenNMT-entmax
https://github.com/deep-spin/S7
https://github.com/deep-spin/sigmorphon-seq2seq
https://github.com/deterministic-algorithms-lab/Large-XLM
https://github.com/dice-group/KG-NMT
https://github.com/dmlc/gluon-nlp
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
https://github.com/duyvuleo/Transformer-DyNet
Incorporating Discrete Translation Lexicons into Neural Machine Translation
https://github.com/facebookresearch/CodeGen
https://github.com/facebookresearch/XLM
https://github.com/facebookresearch/fairseq
https://github.com/facebookresearch/stopes
https://github.com/facebookresearch/vizseq
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
https://github.com/feyzaakyurek/XLM-LwLL
https://github.com/fqyshelly/CS224n-Winter2019-assignment-solutions
Effective Approaches to Attention-based Neural Machine Translation
https://github.com/fshdnc/enfi-XLM
https://github.com/fstahlberg/tensor2tensor-usr
Deep Recurrent Models with Fast-Forward Connections for Neural Machine Translation
https://github.com/gentaiscool/end2end-asr-pytorch
Syllable-Based Sequence-to-Sequence Speech Recognition with the Transformer in Mandarin Chinese
https://github.com/glample/fastBPE
https://github.com/gongshuangshuang/deep-text-corrector
Addressing the Rare Word Problem in Neural Machine Translation
https://github.com/google-research/electra
https://github.com/google-research/language
Consistency by Agreement in Zero-shot Neural Machine Translation
https://github.com/google/wmt19-paraphrased-references
Human-Paraphrased References Improve Neural Machine Translation
https://github.com/gretelai/gretel-synthetics
Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates
https://github.com/guillaume-chevalier/HAR-stacked-residual-bidir-LSTMs
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
https://github.com/guillaume-chevalier/LSTM-Human-Activity-Recognition
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
https://github.com/he1ght/BiBERT_CE
BERT, mBERT, or BiBERT? A Study on Contextualized Embeddings for Neural Machine Translation
https://github.com/hnt4499/seq2seq
Effective Approaches to Attention-based Neural Machine Translation
https://github.com/hokkaido/fake-reviews
Stay On-Topic: Generating Context-specific Fake Restaurant Reviews
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.