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/allenai/sciriff
공식 코드SciRIFF: A Resource to Enhance Language Model Instruction-Following over Scientific Literature
https://github.com/allenai/semantic_fragments
공식 코드What Does My QA Model Know? Devising Controlled Probes using Expert Knowledge
https://github.com/allenai/semanticilp
공식 코드Question Answering as Global Reasoning over Semantic Abstractions
https://github.com/allenai/unifiedqa
공식 코드UnifiedQA: Crossing Format Boundaries With a Single QA System
https://github.com/allenai/unqover
공식 코드https://github.com/allenai/visual-reasoning-rationalization
공식 코드https://github.com/allenai/x-lxmert
공식 코드X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers
https://github.com/alon-albalak/xor-covid
공식 코드https://github.com/aloneirew/coresearch
공식 코드Cross-document Event Coreference Search: Task, Dataset and Modeling
https://github.com/aloriosa/gemformer
공식 코드Uncertainty Guided Global Memory Improves Multi-Hop Question Answering
https://github.com/alpha-vllm/llama2-accessory
공식 코드https://github.com/alpha-vllm/lumina-mgpt
공식 코드https://github.com/alphafin-proj/alphafin
공식 코드AlphaFin: Benchmarking Financial Analysis with Retrieval-Augmented Stock-Chain Framework
https://github.com/alps-lab/trojan-lm
공식 코드https://github.com/amaiya/ktrain
공식 코드https://github.com/amayuelas/knowledge-of-knowledge
공식 코드Knowledge of Knowledge: Exploring Known-Unknowns Uncertainty with Large Language Models
https://github.com/amazon-research/dse
공식 코드Learning Dialogue Representations from Consecutive Utterances
https://github.com/amazon-research/irgr
공식 코드Entailment Tree Explanations via Iterative Retrieval-Generation Reasoner
https://github.com/amazon-research/mintaka
공식 코드Mintaka: A Complex, Natural, and Multilingual Dataset for End-to-End Question Answering
https://github.com/amazon-research/mix-generation
공식 코드https://github.com/amazon-research/qa-dataset-converter
공식 코드https://github.com/amazon-research/question-answer-consolidation
공식 코드https://github.com/amazon-research/semantic-parsing-as-abstractive-qa
공식 코드Compositional Task-Oriented Parsing as Abstractive Question Answering
https://github.com/amazon-research/wqa-cerberus
공식 코드https://github.com/amazon-research/wqa-multi-sentence-inference
공식 코드Paragraph-based Transformer Pre-training for Multi-Sentence Inference
https://github.com/amazon-science/auto-cot
공식 코드Automatic Chain of Thought Prompting in Large Language Models
https://github.com/amazon-science/auto-rag-eval
공식 코드Automated Evaluation of Retrieval-Augmented Language Models with Task-Specific Exam Generation
https://github.com/amazon-science/background-summaries
공식 코드https://github.com/amazon-science/ceret-llm-refine
공식 코드CERET: Cost-Effective Extrinsic Refinement for Text Generation
https://github.com/amazon-science/contextual-product-qa
공식 코드xPQA: Cross-Lingual Product Question Answering across 12 Languages
https://github.com/amazon-science/contextualunderstanding-contrastivedecoding
공식 코드Enhancing Contextual Understanding in Large Language Models through Contrastive Decoding
https://github.com/amazon-science/factual-confidence-of-llms
공식 코드Factual Confidence of LLMs: on Reliability and Robustness of Current Estimators
https://github.com/amazon-science/handling-ontology-gaps-in-semantic-parsing
공식 코드https://github.com/amazon-science/llm-hallucinations-factual-qa
공식 코드On Early Detection of Hallucinations in Factual Question Answering
https://github.com/amazon-science/mm-cot
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.