https://github.com/adaxry/ss_on_decoding_steps
공식 코드Scheduled Sampling Based on Decoding Steps for Neural Machine Translation
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/adaxry/unified_layer_skipping
공식 코드Accelerating Inference in Large Language Models with a Unified Layer Skipping Strategy
https://github.com/adithya7/lambre
공식 코드Evaluating the Morphosyntactic Well-formedness of Generated Texts
https://github.com/agwabom/pema
공식 코드PEMA: An Offsite-Tunable Plug-in External Memory Adaptation for Language Models
https://github.com/ahanps/english-hindi-parallel-corpus
공식 코드Evaluating Machine Translation Models for English-Hindi Language Pairs: A Comparative Analysis
https://github.com/ahmedheakl/arazn-llm
공식 코드ArzEn-LLM: Code-Switched Egyptian Arabic-English Translation and Speech Recognition Using LLMs
https://github.com/ahmetustun/fairseq
공식 코드When does Parameter-Efficient Transfer Learning Work for Machine Translation?
https://github.com/ai4bharat/ctqscorer
공식 코드CTQScorer: Combining Multiple Features for In-context Example Selection for Machine Translation
https://github.com/ai4bharat/indicmt-eval
공식 코드IndicMT Eval: A Dataset to Meta-Evaluate Machine Translation metrics for Indian Languages
https://github.com/ai4bharat/indictrans2
공식 코드https://github.com/aic-factcheck/csfever-and-ctkfacts-paper
공식 코드CsFEVER and CTKFacts: Acquiring Czech data for fact verification
https://github.com/aic-factcheck/multilingual-fact-checking
공식 코드Pipeline and Dataset Generation for Automated Fact-checking in Almost Any Language
https://github.com/aimagelab/meshed-memory-transformer
공식 코드https://github.com/aiphes/discoscore
공식 코드DiscoScore: Evaluating Text Generation with BERT and Discourse Coherence
https://github.com/aitorormazabal/paraphrasing-from-parallel
공식 코드https://github.com/aixplain/Efficient-MT
공식 코드https://github.com/ajd12342/textless-s2st
공식 코드Textless Speech-to-Speech Translation With Limited Parallel Data
https://github.com/ajd12342/unit-speech-translation
공식 코드Textless Speech-to-Speech Translation With Limited Parallel Data
https://github.com/akoksal/silveralign
공식 코드SilverAlign: MT-Based Silver Data Algorithm For Evaluating Word Alignment
https://github.com/alankarj/cross_lingual_ner
공식 코드Entity Projection via Machine Translation for Cross-Lingual NER
https://github.com/alessiogalatolo/viszopro
공식 코드https://github.com/alexa/alexa-point-of-view-dataset
공식 코드Converting the Point of View of Messages Spoken to Virtual Assistants
https://github.com/alexandra-chron/lexical_xlm_relm
공식 코드https://github.com/alexandra-chron/relm_unmt
공식 코드Reusing a Pretrained Language Model on Languages with Limited Corpora for Unsupervised NMT
https://github.com/alexandra-chron/umt-lmu-wmt2020
공식 코드The LMU Munich System for the WMT 2020 Unsupervised Machine Translation Shared Task
https://github.com/aliaraabi/joint_dropout
공식 코드https://github.com/alimrsn79/da_lr_nmt
공식 코드From Priest to Doctor: Domain Adaptaion for Low-Resource Neural Machine Translation
https://github.com/alirezamshi/bias-compressedmt
공식 코드What Do Compressed Multilingual Machine Translation Models Forget?
https://github.com/alirezamshi/small100
공식 코드SMaLL-100: Introducing Shallow Multilingual Machine Translation Model for Low-Resource Languages
https://github.com/alirezaseif/nonmarkovian_learning
공식 코드https://github.com/aliyun/cflue
공식 코드https://github.com/allenai/evaluation-interfaces
공식 코드GENIE: Toward Reproducible and Standardized Human Evaluation for Text Generation
https://github.com/allenai/genie-worker-scoring
공식 코드GENIE: Toward Reproducible and Standardized Human Evaluation for Text Generation
https://github.com/allenschmaltz/grammar
공식 코드https://github.com/alpoktem/MachineDub
공식 코드https://github.com/am-azadi/SemEval2025-Task7-Word2winners
공식 코드Word2winners at SemEval-2025 Task 7: Multilingual and Crosslingual Fact-Checked Claim Retrieval
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.