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/jdcomsearch/jdsearch-22
공식 코드Pre-training Tasks for User Intent Detection and Embedding Retrieval in E-commerce Search
https://github.com/jding0521/graphotter
공식 코드GraphOTTER: Evolving LLM-based Graph Reasoning for Complex Table Question Answering
https://github.com/jefferyzhan/griffon
공식 코드Griffon-G: Bridging Vision-Language and Vision-Centric Tasks via Large Multimodal Models
https://github.com/jeffhj/raven
공식 코드RAVEN: In-Context Learning with Retrieval-Augmented Encoder-Decoder Language Models
https://github.com/jeffreysijuntan/lloco
공식 코드https://github.com/jeffwillette/cascading_kv_cache
공식 코드Training-Free Exponential Context Extension via Cascading KV Cache
https://github.com/jemoka/dropfree
공식 코드https://github.com/jenlindadsouza/NLPContributions
공식 코드https://github.com/jensen-w/retqa
공식 코드RETQA: A Large-Scale Open-Domain Tabular Question Answering Dataset for Real Estate Sector
https://github.com/jensenw1/RETQA
공식 코드RETQA: A Large-Scale Open-Domain Tabular Question Answering Dataset for Real Estate Sector
https://github.com/jeonghun3572/K-COMP
공식 코드K-COMP: Retrieval-Augmented Medical Domain Question Answering With Knowledge-Injected Compressor
https://github.com/jeremy-qin/medical_confidence_elicitation
공식 코드Enhancing Healthcare LLM Trust with Atypical Presentations Recalibration
https://github.com/jerrrynie/cgsn
공식 코드https://github.com/jerrrynie/diverseqa
공식 코드https://github.com/jerrrynie/unsupervised-long-document-qa
공식 코드AttenWalker: Unsupervised Long-Document Question Answering via Attention-based Graph Walking
https://github.com/jerryyli/svitt
공식 코드https://github.com/jetrunner/tupate
공식 코드https://github.com/jgorham/stochastic_stein_discrepancy
공식 코드https://github.com/jh-yi/video-panda
공식 코드Video-Panda: Parameter-efficient Alignment for Encoder-free Video-Language Models
https://github.com/jhwjhw0123/streaming-regret-minimization-mabs
공식 코드Tight Regret Bounds for Single-pass Streaming Multi-armed Bandits
https://github.com/jhyuklee/DensePhrases
공식 코드https://github.com/jhyuklee/sparc
공식 코드Contextualized Sparse Representations for Real-Time Open-Domain Question Answering
https://github.com/ji-youn-kim/ehrnoteqa
공식 코드EHRNoteQA: An LLM Benchmark for Real-World Clinical Practice Using Discharge Summaries
https://github.com/jiajiezou/toa
공식 코드Human Attention during Goal-directed Reading Comprehension Relies on Task Optimization
https://github.com/jialinwu17/mavex
공식 코드https://github.com/jiangjiechen/loren
공식 코드LOREN: Logic-Regularized Reasoning for Interpretable Fact Verification
https://github.com/jiangjiechen/uncommongen
공식 코드Say What You Mean! Large Language Models Speak Too Positively about Negative Commonsense Knowledge
https://github.com/jiangshdd/learningtoselect
공식 코드https://github.com/jiangshdd/reviewcritique
공식 코드LLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewing
https://github.com/jiangsongtao/med-moe
공식 코드Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models
https://github.com/jiangsongtao/tinymed
공식 코드Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models
https://github.com/jiangsongtao/vtprompt
공식 코드https://github.com/jiangycTarheel/Adversarial-MultiHopQA
공식 코드https://github.com/jianyu-cs/promptquine
공식 코드Evolving Prompts In-Context: An Open-ended, Self-replicating Perspective
https://github.com/jiaruifeng/gofa
공식 코드GOFA: A Generative One-For-All Model for Joint Graph Language Modeling
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.