https://github.com/kakaobrain/jejueo
공식 코드Jejueo Datasets for Machine Translation and Speech Synthesis
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
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>
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Jejueo Datasets for Machine Translation and Speech Synthesis
An Empirical Study of Tokenization Strategies for Various Korean NLP Tasks
Non-Exchangeable Conformal Language Generation with Nearest Neighbors
Sequential Large Language Model-Based Hyper-parameter Optimization
Attentive fine-tuning of Transformers for Translation of low-resourced languages @LoResMT 2021
Can you map it to English? The Role of Cross-Lingual Alignment in Multilingual Performance of LLMs
Text Simplification for Comprehension-based Question-Answering
Sinhala Transliteration: A Comparative Analysis Between Rule-based and Seq2Seq Approaches
Exploring Document-Level Literary Machine Translation with Parallel Paragraphs from World Literature
Using Linguistic Typology to Enrich Multilingual Lexicons: the Case of Lexical Gaps in Kinship
SSR-Zero: Simple Self-Rewarding Reinforcement Learning for Machine Translation
PidginUNMT: Unsupervised Neural Machine Translation from West African Pidgin to English
IsoVec: Controlling the Relative Isomorphism of Word Embedding Spaces
Extending the Subwording Model of Multilingual Pretrained Models for New Languages
Using Source-Side Confidence Estimation for Reliable Translation into Unfamiliar Languages
Improving Rare Word Translation With Dictionaries and Attention Masking
Training Deep Neural Networks with Adaptive Momentum Inspired by the Quadratic Optimization
The Importance of Being Recurrent for Modeling Hierarchical Structure
Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback
Grammatical gender associations outweigh topical gender bias in crosslinguistic word embeddings
Navigating the Metrics Maze: Reconciling Score Magnitudes and Accuracies
Multilingual Lexical Simplification via Paraphrase Generation
Rule Learning as Machine Translation using the Atomic Knowledge Bank
Retrieval-Augmented Machine Translation with Unstructured Knowledge
ExTrans: Multilingual Deep Reasoning Translation via Exemplar-Enhanced Reinforcement Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.