https://github.com/pooyafayyaz/gloss2text
공식 코드Gloss2Text: Sign Language Gloss translation using LLMs and Semantically Aware Label Smoothing
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Gloss2Text: Sign Language Gloss translation using LLMs and Semantically Aware Label Smoothing
USCORE: An Effective Approach to Fully Unsupervised Evaluation Metrics for Machine Translation
Planning with Incomplete Information in Quantified Answer Set Programming
Beyond Binary Gender: Evaluating Gender-Inclusive Machine Translation with Ambiguous Attitude Words
Improving Translation Faithfulness of Large Language Models via Augmenting Instructions
Cross-Lingual Adaptation using Structural Correspondence Learning
R-PointHop: A Green, Accurate, and Unsupervised Point Cloud Registration Method
An Empirical Study of In-context Learning in LLMs for Machine Translation
On Creating an English-Thai Code-switched Machine Translation in Medical Domain
PRGFlow: Benchmarking SWAP-Aware Unified Deep Visual Inertial Odometry
SPPL: Probabilistic Programming with Fast Exact Symbolic Inference
Investigating the translation capabilities of Large Language Models trained on parallel data only
CipherDAug: Ciphertext based Data Augmentation for Neural Machine Translation
StyleCLIPDraw: Coupling Content and Style in Text-to-Drawing Translation
Molecular Transformer - A Model for Uncertainty-Calibrated Chemical Reaction Prediction
Image Synthesis with Adversarial Networks: a Comprehensive Survey and Case Studies
Classical Structured Prediction Losses for Sequence to Sequence Learning
Cross-lingual Retrieval for Iterative Self-Supervised Training
Language Models not just for Pre-training: Fast Online Neural Noisy Channel Modeling
Multilingual Denoising Pre-training for Neural Machine Translation
Leveraging Pre-trained Models for FF-to-FFPE Histopathological Image Translation
CoDeF: Content Deformation Fields for Temporally Consistent Video Processing
LLM-Driven Multi-step Translation from C to Rust using Static Analysis
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.