https://github.com/OFA-Sys/ONE-PEACE
공식 코드ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities
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/OceanskySun/GraftNet
공식 코드Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text
https://github.com/OpenBMB/MiniCPM-o
공식 코드https://github.com/OpenRobotLab/Grounded_3D-LLM
공식 코드https://github.com/OpenStellarTeam/ChineseEcomQA
공식 코드ChineseEcomQA: A Scalable E-commerce Concept Evaluation Benchmark for Large Language Models
https://github.com/OpenStellarTeam/UQABench
공식 코드UQABench: Evaluating User Embedding for Prompting LLMs in Personalized Question Answering
https://github.com/OswaldHe/HMT-pytorch
공식 코드HMT: Hierarchical Memory Transformer for Long Context Language Processing
https://github.com/Oxford-AI-for-Society/human-learning-strategies
공식 코드https://github.com/PKU-TANGENT/GAReader-LiveQA
공식 코드https://github.com/PKU-TANGENT/LiveQA
공식 코드https://github.com/PKU-TANGENT/SciDTB
공식 코드SciDTB: Discourse Dependency TreeBank for Scientific Abstracts
https://github.com/PKU-YuanGroup/LLaVA-CoT
공식 코드https://github.com/PKU-YuanGroup/Video-LLaVA
공식 코드Video-LLaVA: Learning United Visual Representation by Alignment Before Projection
https://github.com/PaddlePaddle/ERNIE
공식 코드ERNIE 2.0: A Continual Pre-training Framework for Language Understanding
https://github.com/PaddlePaddle/Knover/tree/develop/projects/QKConv
공식 코드Query Enhanced Knowledge-Intensive Conversation via Unsupervised Joint Modeling
https://github.com/PaddlePaddle/PaddleNLP/tree/develop/model_zoo/ernie-1.0
공식 코드ERNIE: Enhanced Representation through Knowledge Integration
https://github.com/PaddlePaddle/PaddleNLP/tree/develop/model_zoo/ernie-layout
공식 코드ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding
https://github.com/PaddlePaddle/PaddleNLP/tree/develop/paddlenlp/transformers/ernie_doc
공식 코드ERNIE-Doc: A Retrospective Long-Document Modeling Transformer
https://github.com/PaddlePaddle/PaddleVideo/blob/develop/docs/en/model_zoo/multimodal/actbert.md
공식 코드https://github.com/PaddlePaddle/Research
공식 코드PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable
https://github.com/PaddlePaddle/XWorld
공식 코드Interactive Grounded Language Acquisition and Generalization in a 2D World
https://github.com/Panda-Peter/image-captioning
공식 코드https://github.com/Paranioar/UniPT
공식 코드UniPT: Universal Parallel Tuning for Transfer Learning with Efficient Parameter and Memory
https://github.com/Park-ing-lot/Imagine
공식 코드https://github.com/PascalSun/TimelineKGQA
공식 코드TimelineKGQA: A Comprehensive Question-Answer Pair Generator for Temporal Knowledge Graphs
https://github.com/PengfeiHePower/ReasonAgent
공식 코드Make LLMs better zero-shot reasoners: Structure-orientated autonomous reasoning
https://github.com/Perevalov/intent_classifier
공식 코드https://github.com/PetarV-/GAT
공식 코드https://github.com/PhilippChr/CLOCQ
공식 코드https://github.com/PhilippChr/CONVEX
공식 코드https://github.com/PhoebusSi/SAR
공식 코드Check It Again: Progressive Visual Question Answering via Visual Entailment
https://github.com/Phrase-in-Context/eval
공식 코드PiC: A Phrase-in-Context Dataset for Phrase Understanding and Semantic Search
https://github.com/PlanTL-GOB-ES/lm-spanish
공식 코드https://github.com/PlanTL-SANIDAD/lm-spanish
공식 코드https://github.com/PlusLabNLP/Re-ReST
공식 코드Re-ReST: Reflection-Reinforced Self-Training for Language Agents
https://github.com/PluviophileYU/CVC-QA
공식 코드Counterfactual Variable Control for Robust and Interpretable Question Answering
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.