https://github.com/tzshi/squall
공식 코드On the Potential of Lexico-logical Alignments for Semantic Parsing to SQL Queries
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/ubc-nlp/arastories
공식 코드Arabic Automatic Story Generation with Large Language Models
https://github.com/ubc-nlp/llmas
공식 코드LLM Performance Predictors are good initializers for Architecture Search
https://github.com/ubc-nlp/mos
공식 코드https://github.com/ubc-nlp/turjuman
공식 코드TURJUMAN: A Public Toolkit for Neural Arabic Machine Translation
https://github.com/uber/ludwig
공식 코드https://github.com/uclaml/dndm
공식 코드Fast Sampling via Discrete Non-Markov Diffusion Models with Predetermined Transition Time
https://github.com/uds-lsv/3st
공식 코드Exploiting Social Media Content for Self-Supervised Style Transfer
https://github.com/uds-lsv/aadam
공식 코드https://github.com/ufal/MT-metrics-in-SimST
공식 코드MT Metrics Correlate with Human Ratings of Simultaneous Speech Translation
https://github.com/ufal/kazitext
공식 코드Understanding Model Robustness to User-generated Noisy Texts
https://github.com/ufal/legros
공식 코드https://github.com/ufal/legros-paper
공식 코드https://github.com/ufal/low-resource-gec-wnut2019
공식 코드https://github.com/ufal/neuralmonkey
공식 코드Attention Strategies for Multi-Source Sequence-to-Sequence Learning
https://github.com/ufal/optimal-reference-translations
공식 코드https://github.com/ulab-uiuc/consistencychecker
공식 코드ConsistencyChecker: Tree-based Evaluation of LLM Generalization Capabilities
https://github.com/ulugbeksalaev/uztransliterator
공식 코드https://github.com/umair-nasir14/ngdc
공식 코드https://github.com/unicamp-dl/Lite-T5-Translation
공식 코드Lite Training Strategies for Portuguese-English and English-Portuguese Translation
https://github.com/unicamp-dl/mMARCO
공식 코드mMARCO: A Multilingual Version of the MS MARCO Passage Ranking Dataset
https://github.com/uralik/oversmoothing_rate
공식 코드Characterizing and addressing the issue of oversmoothing in neural autoregressive sequence modeling
https://github.com/urvashik/knnlm
공식 코드https://github.com/utsjiyaoli/qa-attack
공식 코드Deceiving Question-Answering Models: A Hybrid Word-Level Adversarial Approach
https://github.com/vania-mendonca/MTOL
공식 코드https://github.com/vania-mendonca/Onception
공식 코드Onception: Active Learning with Expert Advice for Real World Machine Translation
https://github.com/varungumma/fairseq
공식 코드https://github.com/vernadankers/mt_idioms
공식 코드Can Transformer be Too Compositional? Analysing Idiom Processing in Neural Machine Translation
https://github.com/vicentvankor/sun-shine
공식 코드https://github.com/vicmak/Exploiting-BiLSTM-for-Proper-Word-Choice
공식 코드Choosing the Right Word: Using Bidirectional LSTM Tagger for Writing Support Systems
https://github.com/victor812-hub/entity_datasets
공식 코드How Good are LLMs at Relation Extraction under Low-Resource Scenario? Comprehensive Evaluation
https://github.com/victorwz/zs-nmt-dae
공식 코드Rethinking Zero-shot Neural Machine Translation: From a Perspective of Latent Variables
https://github.com/vietai/mTet
공식 코드https://github.com/vinairesearch/phomt
공식 코드PhoMT: A High-Quality and Large-Scale Benchmark Dataset for Vietnamese-English Machine Translation
https://github.com/vineet2104/adversarialtrainingfordisfluencycorrection
공식 코드https://github.com/vineet2104/disco
공식 코드DISCO: A Large Scale Human Annotated Corpus for Disfluency Correction in Indo-European Languages
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.