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/awwkl/brain_language_narratives
공식 코드Training language models to summarize narratives improves brain alignment
https://github.com/awwkl/brain_language_summarization
공식 코드Training language models to summarize narratives improves brain alignment
https://github.com/ayesha-ishaq/drivelmm-o1
공식 코드https://github.com/ayushjain1144/NukeBERT
공식 코드NukeBERT: A Pre-trained language model for Low Resource Nuclear Domain
https://github.com/azreasoners/llm-asp
공식 코드Coupling Large Language Models with Logic Programming for Robust and General Reasoning from Text
https://github.com/baai-dcai/m3d
공식 코드M3D: Advancing 3D Medical Image Analysis with Multi-Modal Large Language Models
https://github.com/baai-dcai/visual-instruction-tuning
공식 코드https://github.com/baaivision/emu
공식 코드https://github.com/babangain/unsup_questions_translation
공식 코드Reference Free Domain Adaptation for Translation of Noisy Questions with Question Specific Rewards
https://github.com/backpropper/cbc-emecom
공식 코드Capacity, Bandwidth, and Compositionality in Emergent Language Learning
https://github.com/baeseongsu/ehrxqa
공식 코드https://github.com/baeseongsu/mimic-cxr-vqa
공식 코드https://github.com/baharanm/craig
공식 코드Coresets for Data-efficient Training of Machine Learning Models
https://github.com/bahuia/aqgnet
공식 코드https://github.com/bahuia/hgnet
공식 코드https://github.com/bai-lab/kg-retriever
공식 코드KG-Retriever: Efficient Knowledge Indexing for Retrieval-Augmented Large Language Models
https://github.com/baichuan-inc/baichuan-audio
공식 코드Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction
https://github.com/baidu-research/GloballyNormalizedReader
공식 코드https://github.com/bailuding/rails
공식 코드https://github.com/banglab-udem-mila/nlp4matsci-acl23
공식 코드https://github.com/bangliu/ACS-QG
공식 코드Asking Questions the Human Way: Scalable Question-Answer Generation from Text Corpus
https://github.com/baohaoliao/mefts
공식 코드Make Pre-trained Model Reversible: From Parameter to Memory Efficient Fine-Tuning
https://github.com/barshana-banerjee/ParaQA
공식 코드ParaQA: A Question Answering Dataset with Paraphrase Responses for Single-Turn Conversation
https://github.com/bashlab/llasa
공식 코드LLaSA: A Multimodal LLM for Human Activity Analysis Through Wearable and Smartphone Sensors
https://github.com/bashlab/raven
공식 코드https://github.com/batsresearch/bonito
공식 코드Learning to Generate Instruction Tuning Datasets for Zero-Shot Task Adaptation
https://github.com/bayer-group/text-to-sql-epi-ehr-naacl2024
공식 코드https://github.com/bbuing9/iclr24_sure
공식 코드SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs
https://github.com/bcdnlp/prd
공식 코드PRD: Peer Rank and Discussion Improve Large Language Model based Evaluations
https://github.com/bcdnlp/structure-qa
공식 코드Leveraging Structured Information for Explainable Multi-hop Question Answering and Reasoning
https://github.com/bcmi/causal-vidqa
공식 코드https://github.com/bdhingra/ga-reader
공식 코드https://github.com/bdhingra/quasar
공식 코드Quasar: Datasets for Question Answering by Search and Reading
https://github.com/beckschen/llavolta
공식 코드Efficient Large Multi-modal Models via Visual Context Compression
https://github.com/becomebright/rekv
공식 코드Streaming Video Question-Answering with In-context Video KV-Cache Retrieval
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.