https://github.com/allanj/deductive-mwp
공식 코드Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
The goal of Relational Reasoning is to figure out the relationships among different entities, such as image pixels, words or sentences, human skeletons or interactive moving agents.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction
Breakpoint Transformers for Modeling and Tracking Intermediate Beliefs
Leveraging Relational Information for Learning Weakly Disentangled Representations
TGraphX: Tensor-Aware Graph Neural Network for Multi-Dimensional Feature Learning
Relational reasoning and generalization using non-symbolic neural networks
Disentangling and Integrating Relational and Sensory Information in Transformer Architectures
ORCHARD: A Benchmark For Measuring Systematic Generalization of Multi-Hierarchical Reasoning
Reconstructing Groups of People with Hypergraph Relational Reasoning
Benchmarking and Understanding Compositional Relational Reasoning of LLMs
Visual Relationship Detection with Visual-Linguistic Knowledge from Multimodal Representations
Relational inductive biases, deep learning, and graph networks
IRRGN: An Implicit Relational Reasoning Graph Network for Multi-turn Response Selection
Learning from Protein Structure with Geometric Vector Perceptrons
BayReL: Bayesian Relational Learning for Multi-omics Data Integration
CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Text
Computer-aided Tuberculosis Diagnosis with Attribute Reasoning Assistance
Differentially Private Relational Learning with Entity-level Privacy Guarantees
Privately Learning from Graphs with Applications in Fine-tuning Large Language Models
Self-Supervised Time Series Representation Learning by Inter-Intra Relational Reasoning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.