https://github.com/yilinyang7/fairseq_multi_fix
공식 코드Improving Multilingual Translation by Representation and Gradient Regularization
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/yimeng0701/CKD_pytorch
공식 코드Why Skip If You Can Combine: A Simple Knowledge Distillation Technique for Intermediate Layers
https://github.com/yinzhangyue/c2fm
공식 코드https://github.com/yinzhangyue/smoothing-r3
공식 코드https://github.com/yixinL7/Direct-Style-Transfer
공식 코드https://github.com/yli1/CGPS
공식 코드https://github.com/ymoslem/WLAC
공식 코드Translation Word-Level Auto-Completion: What can we achieve out of the box?
https://github.com/ymoslem/adaptive-mt-llm
공식 코드https://github.com/ymoslem/adaptive-mt-llm-fine-tuning
공식 코드Fine-tuning Large Language Models for Adaptive Machine Translation
https://github.com/ymoslem/mt-lm
공식 코드https://github.com/ymoslem/mt-preparation
공식 코드https://github.com/ynklab/SGET
공식 코드Evaluating Structural Generalization in Neural Machine Translation
https://github.com/ynklab/xcodesearchnet
공식 코드Constructing Multilingual Code Search Dataset Using Neural Machine Translation
https://github.com/yogarshi/SemDiverge
공식 코드Identifying Semantic Divergences in Parallel Text without Annotations
https://github.com/yongchanghao/multi-task-nat
공식 코드Multi-Task Learning with Shared Encoder for Non-Autoregressive Machine Translation
https://github.com/yoonkim/neural-qcfg
공식 코드https://github.com/youblei/prompt-space
공식 코드Prompt Space Optimizing Few-shot Reasoning Success with Large Language Models
https://github.com/ys-zong/awesome-self-supervised-multimodal-learning
공식 코드https://github.com/ysngki/xmoe
공식 코드XMoE: Sparse Models with Fine-grained and Adaptive Expert Selection
https://github.com/yubowenok/flowsense
공식 코드FlowSense: A Natural Language Interface for Visual Data Exploration within a Dataflow System
https://github.com/yuchen005/gentranslate
공식 코드GenTranslate: Large Language Models are Generative Multilingual Speech and Machine Translators
https://github.com/yuedongP/EditNTS
공식 코드EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
https://github.com/yulu-dada/learned-conf-nmt
공식 코드Learning Confidence for Transformer-based Neural Machine Translation
https://github.com/yunhaoyang234/Multi-Filter-Seq2Seq-Model
공식 코드https://github.com/yunsukim86/sockeye-transfer
공식 코드Effective Cross-lingual Transfer of Neural Machine Translation Models without Shared Vocabularies
https://github.com/yutongwang1216/docmtagent
공식 코드DelTA: An Online Document-Level Translation Agent Based on Multi-Level Memory
https://github.com/yutongwang1216/reflectionllmmt
공식 코드TasTe: Teaching Large Language Models to Translate through Self-Reflection
https://github.com/yx-lu/benchmarking-llms--judgments-with-no-gold-standard
공식 코드https://github.com/yxuansu/NAG-BERT
공식 코드Non-Autoregressive Text Generation with Pre-trained Language Models
https://github.com/yxwan123/logicasker
공식 코드LogicAsker: Evaluating and Improving the Logical Reasoning Ability of Large Language Models
https://github.com/yy-ye/mqm-analysis
공식 코드https://github.com/yzh119/BPT
공식 코드BP-Transformer: Modelling Long-Range Context via Binary Partitioning
https://github.com/yzpang/gold-off-policy-text-gen-iclr21
공식 코드https://github.com/zanchangtong/ptvsri
공식 코드https://github.com/zanchangtong/unions
공식 코드Unlikelihood Tuning on Negative Samples Amazingly Improves Zero-Shot Translation
https://github.com/zdou0830/DAFE
공식 코드Unsupervised Domain Adaptation for Neural Machine Translation with Domain-Aware Feature Embeddings
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.