https://github.com/gaosx2000/sg_kbqa
공식 코드Beyond Seen Data: Improving KBQA Generalization Through Schema-Guided Logical Form Generation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
A methodology that involves selecting relevant data or examples from a large dataset to support tasks like prediction, learning, or inference. It enhances models by providing context or additional information, often used in systems like retrieval-augmented generation or in-context learning.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Beyond Seen Data: Improving KBQA Generalization Through Schema-Guided Logical Form Generation
LooPy: A Research-Friendly Mix Framework for Music Information Retrieval on Electronic Dance Music
How to Configure Good In-Context Sequence for Visual Question Answering
Scale-Free Image Keypoints Using Differentiable Persistent Homology
Are Local Features All You Need for Cross-Domain Visual Place Recognition?
Symbolic inductive bias for visually grounded learning of spoken language
IRGAN: A Minimax Game for Unifying Generative and Discriminative Information Retrieval Models
Bidirectional End-to-End Learning of Retriever-Reader Paradigm for Entity Linking
Automatic Context Pattern Generation for Entity Set Expansion
Semantically-Enriched Search Engine for Geoportals: A Case Study with ArcGIS Online
Siamese Vision Transformers are Scalable Audio-visual Learners
Automatic Generation of Fashion Images using Prompting in Generative Machine Learning Models
Extracting Event-Centric Document Collections from Large-Scale Web Archives
Zep: A Temporal Knowledge Graph Architecture for Agent Memory
Robust Cross-Modal Knowledge Distillation for Unconstrained Videos
On the Impact of Entity Linking in Microblog Real-Time Filtering
Optimizing Intermediate Representations of Generative Models for Phase Retrieval
Weakly Supervised Deep Hyperspherical Quantization for Image Retrieval
Contrastive Quantization with Code Memory for Unsupervised Image Retrieval
Hybrid Contrastive Quantization for Efficient Cross-View Video Retrieval
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.