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/alkaidpku/dq-toolqa
공식 코드https://github.com/allanj/deductive-mwp
공식 코드Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction
https://github.com/allegro/klejbenchmark-baselines
공식 코드KLEJ: Comprehensive Benchmark for Polish Language Understanding
https://github.com/allen-li1231/refiner-rag
공식 코드Refiner: Restructure Retrieval Content Efficiently to Advance Question-Answering Capabilities
https://github.com/allen-li1231/treehop-rag
공식 코드TreeHop: Generate and Filter Next Query Embeddings Efficiently for Multi-hop Question Answering
https://github.com/allenai/ai2-scholarqa-lib
공식 코드Ai2 Scholar QA: Organized Literature Synthesis with Attribution
https://github.com/allenai/ai2thor
공식 코드https://github.com/allenai/aokvqa
공식 코드A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge
https://github.com/allenai/arc-solvers
공식 코드Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering
https://github.com/allenai/bi-att-flow
공식 코드https://github.com/allenai/close
공식 코드I Can't Believe There's No Images! Learning Visual Tasks Using only Language Supervision
https://github.com/allenai/document-qa
공식 코드https://github.com/allenai/dream
공식 코드DREAM: Improving Situational QA by First Elaborating the Situation
https://github.com/allenai/easy-to-hard-generalization
공식 코드The Unreasonable Effectiveness of Easy Training Data for Hard Tasks
https://github.com/allenai/embeddingrecycling
공식 코드https://github.com/allenai/ethical-interventions
공식 코드Ethical-Advice Taker: Do Language Models Understand Natural Language Interventions?
https://github.com/allenai/gooaq
공식 코드https://github.com/allenai/gpv-1
공식 코드https://github.com/allenai/grit_official
공식 코드https://github.com/allenai/label_rationale_association
공식 코드Measuring Association Between Labels and Free-Text Rationales
https://github.com/allenai/lila
공식 코드https://github.com/allenai/longformer
공식 코드https://github.com/allenai/lumos
공식 코드Agent Lumos: Unified and Modular Training for Open-Source Language Agents
https://github.com/allenai/macaw
공식 코드https://github.com/allenai/mice
공식 코드Explaining NLP Models via Minimal Contrastive Editing (MiCE)
https://github.com/allenai/missing-fact
공식 코드What's Missing: A Knowledge Gap Guided Approach for Multi-hop Question Answering
https://github.com/allenai/modularqa
공식 코드Text Modular Networks: Learning to Decompose Tasks in the Language of Existing Models
https://github.com/allenai/natural-instructions
공식 코드Cross-Task Generalization via Natural Language Crowdsourcing Instructions
https://github.com/allenai/natural-instructions-v1
공식 코드Cross-Task Generalization via Natural Language Crowdsourcing Instructions
https://github.com/allenai/open_vocab_semparse
공식 코드Open-Vocabulary Semantic Parsing with both Distributional Statistics and Formal Knowledge
https://github.com/allenai/openpi-dataset
공식 코드https://github.com/allenai/qasc
공식 코드QASC: A Dataset for Question Answering via Sentence Composition
https://github.com/allenai/qasper-led-baseline
공식 코드A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers
https://github.com/allenai/rainbow
공식 코드UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask Benchmark
https://github.com/allenai/s2abel
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.