https://github.com/zjukg/morse
공식 코드Meta-Knowledge Transfer for Inductive Knowledge Graph Embedding
Papers with Code 아카이브
Question Answering
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 19
- 평가표
- 153
- 보존된 평가 기록
- 1,781
Question answering can be segmented into domain-specific tasks like community question answering and knowledge-base question answering. Popular benchmark datasets for evaluation question answering systems include SQuAD, HotPotQA, bAbI, TriviaQA, WikiQA, and many others. Models for question answering are typically evaluated on metrics like EM and F1. Some recent top performing models are T5 and XLNet.
( Image credit: SQuAD )
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/zjukg/trustuqa
공식 코드TrustUQA: A Trustful Framework for Unified Structured Data Question Answering
https://github.com/zjunlp/Kformer
공식 코드Kformer: Knowledge Injection in Transformer Feed-Forward Layers
https://github.com/zjunlp/MKGformer
공식 코드Hybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completion
https://github.com/zjunlp/autoact
공식 코드AutoAct: Automatic Agent Learning from Scratch for QA via Self-Planning
https://github.com/zjunlp/autokg
공식 코드LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future Opportunities
https://github.com/zjunlp/easyedit
공식 코드WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models
https://github.com/zjunlp/mol-instructions
공식 코드Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models
https://github.com/zjunlp/promptkg
공식 코드LambdaKG: A Library for Pre-trained Language Model-Based Knowledge Graph Embeddings
https://github.com/zjunlp/relphormer
공식 코드Relphormer: Relational Graph Transformer for Knowledge Graph Representations
https://github.com/zl-liu/radiation-oncology-nlp-database
공식 코드https://github.com/zlccccc/3dgqa
공식 코드Towards Explainable 3D Grounded Visual Question Answering: A New Benchmark and Strong Baseline
https://github.com/zli12321/qa_metrics
공식 코드PEDANTS: Cheap but Effective and Interpretable Answer Equivalence
https://github.com/zlin7/contextsl
공식 코드Contextualized Sequence Likelihood: Enhanced Confidence Scores for Natural Language Generation
https://github.com/zlin7/uq-nlg
공식 코드Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models
https://github.com/zmd971202/OpenNER
공식 코드Neural Correction Model for Open-Domain Named Entity Recognition
https://github.com/zmtkeke/IRN
공식 코드An Interpretable Reasoning Network for Multi-Relation Question Answering
https://github.com/zmy-9/sfkt
공식 코드https://github.com/zongqianli/pt-moe
공식 코드PT-MoE: An Efficient Finetuning Framework for Integrating Mixture-of-Experts into Prompt Tuning
https://github.com/zorazrw/filco
공식 코드Learning to Filter Context for Retrieval-Augmented Generation
https://github.com/zorazrw/nqt-retrieval
공식 코드Table Retrieval May Not Necessitate Table-specific Model Design
https://github.com/zorazrw/trove
공식 코드TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Tasks
https://github.com/zorikg/marcqap
공식 코드https://github.com/zou-group/avatar
공식 코드AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning
https://github.com/zou-group/textgrad
공식 코드https://github.com/zouharvi/kb-shrink
공식 코드Knowledge Base Index Compression via Dimensionality and Precision Reduction
https://github.com/zqs1943/docie
공식 코드EA$^2$E: Improving Consistency with Event Awareness for Document-Level Argument Extraction
https://github.com/zrrskywalker/llama-adapter
공식 코드LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model
https://github.com/zrrskywalker/point-m2ae
공식 코드Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training
https://github.com/zrw00/graceful
공식 코드Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining
https://github.com/zswvivi/ecml_pqa
공식 코드Less is More: Rejecting Unreliable Reviews for Product Question Answering
https://github.com/zted/sbvqa
공식 코드https://github.com/zukangy/kgp-curiousllm
공식 코드CuriousLLM: Elevating Multi-Document QA with Reasoning-Infused Knowledge Graph Prompting
https://github.com/zuucan/needleinahaystack-plus
공식 코드LongAgent: Scaling Language Models to 128k Context through Multi-Agent Collaboration
https://github.com/zwq2018/multi-view-consistency-for-mwp
공식 코드Multi-View Reasoning: Consistent Contrastive Learning for Math Word Problem
https://github.com/zwq803/mm-skin
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.