Papers with Code 아카이브

Machine Translation

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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/ictnlp/BoN-NAT

공식 코드

Minimizing the Bag-of-Ngrams Difference for Non-Autoregressive Neural Machine Translation

https://github.com/ictnlp/DST

공식 코드

Decoder-only Streaming Transformer for Simultaneous Translation

https://github.com/ictnlp/DiverseNMT

공식 코드

Modeling Fluency and Faithfulness for Diverse Neural Machine Translation

https://github.com/ictnlp/GS4NMT

공식 코드

Greedy Search with Probabilistic N-gram Matching for Neural Machine Translation

https://github.com/ictnlp/NA-MNMT

공식 코드

Importance-based Neuron Allocation for Multilingual Neural Machine Translation

https://github.com/ictnlp/PTE-NMT

공식 코드

Pruning-then-Expanding Model for Domain Adaptation of Neural Machine Translation

https://github.com/ictnlp/RSI-NAT

공식 코드

Retrieving Sequential Information for Non-Autoregressive Neural Machine Translation

https://github.com/ictnlp/Seq-NAT

공식 코드

Sequence-Level Training for Non-Autoregressive Neural Machine Translation

https://github.com/ictnlp/TLAT-NMT

공식 코드

Token-level Adaptive Training for Neural Machine Translation

https://github.com/ictnlp/bs-simt

공식 코드

Learning Optimal Policy for Simultaneous Machine Translation via Binary Search

https://github.com/ictnlp/bt4st

공식 코드

Back Translation for Speech-to-text Translation Without Transcripts

https://github.com/ictnlp/cmot

공식 코드

CMOT: Cross-modal Mixup via Optimal Transport for Speech Translation

https://github.com/ictnlp/cokd

공식 코드

Overcoming Catastrophic Forgetting beyond Continual Learning: Balanced Training for Neural Machine Translation

https://github.com/ictnlp/cress

공식 코드

Understanding and Bridging the Modality Gap for Speech Translation

https://github.com/ictnlp/ctc-s2ut

공식 코드

CTC-based Non-autoregressive Textless Speech-to-Speech Translation

https://github.com/ictnlp/ddrs-nat

공식 코드

One Reference Is Not Enough: Diverse Distillation with Reference Selection for Non-Autoregressive Translation

https://github.com/ictnlp/dual-paths

공식 코드

Modeling Dual Read/Write Paths for Simultaneous Machine Translation

https://github.com/ictnlp/fa-dat

공식 코드

Fuzzy Alignments in Directed Acyclic Graph for Non-Autoregressive Machine Translation

https://github.com/ictnlp/glance-simt

공식 코드

Glancing Future for Simultaneous Machine Translation

https://github.com/ictnlp/gma

공식 코드

Gaussian Multi-head Attention for Simultaneous Machine Translation

https://github.com/ictnlp/hmt

공식 코드

Hidden Markov Transformer for Simultaneous Machine Translation

https://github.com/ictnlp/itst

공식 코드

Information-Transport-based Policy for Simultaneous Translation

https://github.com/ictnlp/lfr-nmt

공식 코드

Continual Learning of Neural Machine Translation within Low Forgetting Risk Regions

https://github.com/ictnlp/lnmt-ca

공식 코드

Low-resource Neural Machine Translation with Cross-modal Alignment

https://github.com/ictnlp/moce

공식 코드

MoCE: Adaptive Mixture of Contextualization Experts for Byte-based Neural Machine Translation

https://github.com/ictnlp/moe-waitk

공식 코드

Universal Simultaneous Machine Translation with Mixture-of-Experts Wait-k Policy

https://github.com/ictnlp/multiscale-contextualization

공식 코드

Integrating Multi-scale Contextualized Information for Byte-based Neural Machine Translation

https://github.com/ictnlp/nast

공식 코드

Non-autoregressive Streaming Transformer for Simultaneous Translation

https://github.com/ictnlp/nmla-nat

공식 코드

Non-Monotonic Latent Alignments for CTC-Based Non-Autoregressive Machine Translation

https://github.com/ictnlp/pcfg-nat

공식 코드

Non-autoregressive Machine Translation with Probabilistic Context-free Grammar

https://github.com/ictnlp/ped-simt

공식 코드

Turning Fixed to Adaptive: Integrating Post-Evaluation into Simultaneous Machine Translation

https://github.com/ictnlp/pluvr

공식 코드

Neural Machine Translation with Phrase-Level Universal Visual Representations

https://github.com/ictnlp/sammt

공식 코드

Bridging the Gap between Synthetic and Authentic Images for Multimodal Machine Translation

https://github.com/ictnlp/semling-mnmt

공식 코드

Improving Multilingual Neural Machine Translation by Utilizing Semantic and Linguistic Features

https://github.com/ictnlp/sillm

공식 코드

SiLLM: Large Language Models for Simultaneous Machine Translation

https://github.com/ictnlp/stemm

공식 코드

STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.