https://github.com/zifengcheng/cp
공식 코드Contrastive Prompting Enhances Sentence Embeddings in LLMs through Inference-Time Steering
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Contrastive Prompting Enhances Sentence Embeddings in LLMs through Inference-Time Steering
Unsupervised Sentence Textual Similarity with Compositional Phrase Semantics
Integrating Knowledge Graph embedding and pretrained Language Models in Hypercomplex Spaces
Categorical Metadata Representation for Customized Text Classification
Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos
SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning
Target-oriented Sentiment Classification with Sequential Cross-modal Semantic Graph
MLBiNet: A Cross-Sentence Collective Event Detection Network
Towards Realistic Low-resource Relation Extraction: A Benchmark with Empirical Baseline Study
Towards Realistic Low-resource Relation Extraction: A Benchmark with Empirical Baseline Study
Cross-lingual Spoken Language Understanding with Regularized Representation Alignment
Multi-Modal Interaction Graph Convolutional Network for Temporal Language Localization in Videos
TokAlign: Efficient Vocabulary Adaptation via Token Alignment
Iterative Refinement in the Continuous Space for Non-Autoregressive Neural Machine Translation
Paragraph-level Citation Recommendation based on Topic Sentences as Queries
Poor Man's Quality Estimation: Predicting Reference-Based MT Metrics Without the Reference
Fusing Sentence Embeddings Into LSTM-based Autoregressive Language Models
Unsupervised Sentence Compression using Denoising Auto-Encoders
BLESS: Benchmarking Large Language Models on Sentence Simplification
NMTScore: A Multilingual Analysis of Translation-based Text Similarity Measures
Towards Unsupervised Recognition of Token-level Semantic Differences in Related Documents
An Open-Source Gloss-Based Baseline for Spoken to Signed Language Translation
RE-Matching: A Fine-Grained Semantic Matching Method for Zero-Shot Relation Extraction
Exploring Human-Like Translation Strategy with Large Language Models
SHINE: Saliency-aware HIerarchical NEgative Ranking for Compositional Temporal Grounding
Improving One-stage Visual Grounding by Recursive Sub-query Construction
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.