https://github.com/timotheemickus/seq2seq-splat
공식 코드Why bother with geometry? On the relevance of linear decompositions of Transformer embeddings
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/timpal0l/ScandiSent
공식 코드Should we Stop Training More Monolingual Models, and Simply Use Machine Translation Instead?
https://github.com/timpal0l/sts-benchmark-swedish
공식 코드Why Not Simply Translate? A First Swedish Evaluation Benchmark for Semantic Similarity
https://github.com/tjunlp-lab/commonmt
공식 코드The Box is in the Pen: Evaluating Commonsense Reasoning in Neural Machine Translation
https://github.com/tjunlp-lab/id-zh-mtrobusteval
공식 코드An Empirical Study on the Robustness of Massively Multilingual Neural Machine Translation
https://github.com/tjunlp-lab/pckmt
공식 코드Efficient Cluster-Based k-Nearest-Neighbor Machine Translation
https://github.com/tnq177/improving_lexical_choice_in_nmt
공식 코드https://github.com/tnq177/transformers_without_tears
공식 코드Transformers without Tears: Improving the Normalization of Self-Attention
https://github.com/tomlimi/MT-Tokenizer-Bias
공식 코드https://github.com/tomsherborne/bootstrap
공식 코드https://github.com/tomsherborne/xgr
공식 코드https://github.com/tomsherborne/zx-parse
공식 코드https://github.com/tongxiao2002/dualgeosolver
공식 코드Learning to Solve Geometry Problems via Simulating Human Dual-Reasoning Process
https://github.com/toshohirasawa/mst
공식 코드https://github.com/toshohirasawa/nmtpytorch-emb-pred
공식 코드https://github.com/tosingithub/idesk
공식 코드Potential Idiomatic Expression (PIE)-English: Corpus for Classes of Idioms
https://github.com/trangvu/guda
공식 코드https://github.com/transducens/matilda
공식 코드Non-Fluent Synthetic Target-Language Data Improve Neural Machine Translation
https://github.com/transducens/mayanv
공식 코드https://github.com/transducens/mtl-da-emnlp
공식 코드https://github.com/translatorswb/TWB-MT
공식 코드Tigrinya Neural Machine Translation with Transfer Learning for Humanitarian Response
https://github.com/trusthlt/dp-nmt
공식 코드https://github.com/trusthlt/granularity-is-crucial-dp
공식 코드https://github.com/tshi04/NATS
공식 코드Neural Abstractive Text Summarization with Sequence-to-Sequence Models
https://github.com/tsuruoka-lab/AMI-Meeting-Parallel-Corpus
공식 코드Document-aligned Japanese-English Conversation Parallel Corpus
https://github.com/tsuruoka-lab/BSD
공식 코드https://github.com/tuanh23/multimodalst
공식 코드https://github.com/tuanh23/perturbation-basedqe
공식 코드https://github.com/tuhinjubcse/poetrytranslationemnlp2021
공식 코드Don't Go Far Off: An Empirical Study on Neural Poetry Translation
https://github.com/turkic-interlingua/til-mt
공식 코드Evaluating Multiway Multilingual NMT in the Turkic Languages
https://github.com/tushar117/Transformer-Models-for-Text-Coherence-Assessment
공식 코드https://github.com/tuzhaopeng/LC-NMT
공식 코드Exploiting Cross-Sentence Context for Neural Machine Translation
https://github.com/tuzhaopeng/NMT-Coverage
공식 코드https://github.com/tuzhaopeng/nmt
공식 코드https://github.com/twadada/multilingual-nlm
공식 코드https://github.com/tyliupku/Arbitrary-Order-Infnet
공식 코드An Exploration of Arbitrary-Order Sequence Labeling via Energy-Based Inference Networks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.