https://github.com/CLARIN-PL/PUGG
공식 코드Developing PUGG for Polish: A Modern Approach to KBQA, MRC, and IR Dataset Construction
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Knowledge Base Q&A is the task of answering questions from a knowledge base.
<span style="color:grey; opacity: 0.6">( Image credit: Modeling Semantics with Gated Graph Neural Networks for Knowledge Base Question Answering )</span>
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Developing PUGG for Polish: A Modern Approach to KBQA, MRC, and IR Dataset Construction
Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning
Few-Shot Complex Knowledge Base Question Answering via Meta Reinforcement Learning
KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning
Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signals
Falcon 2.0: An Entity and Relation Linking Tool over Wikidata
Question Decomposition Tree for Answering Complex Questions over Knowledge Bases
A Universal Question-Answering Platform for Knowledge Graphs
Semantic Parsing with Candidate Expressions for Knowledge Base Question Answering
GETT-QA: Graph Embedding based T2T Transformer for Knowledge Graph Question Answering
Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Bases
Don't Generate, Discriminate: A Proposal for Grounding Language Models to Real-World Environments
Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation
Bridging the KB-Text Gap: Leveraging Structured Knowledge-aware Pre-training for KBQA
Beyond Seen Data: Improving KBQA Generalization Through Schema-Guided Logical Form Generation
Bidirectional Attentive Memory Networks for Question Answering over Knowledge Bases
FlexKBQA: A Flexible LLM-Powered Framework for Few-Shot Knowledge Base Question Answering
KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search
Few-shot In-context Learning for Knowledge Base Question Answering
CypherBench: Towards Precise Retrieval over Full-scale Modern Knowledge Graphs in the LLM Era
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.