Papers with Code 아카이브

Question Answering

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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/evansh666/evogen

공식 코드

Progressive Compositionality In Text-to-Image Generative Models

https://github.com/evaportelance/vqa-function-word-learning

공식 코드

Learning the meanings of function words from grounded language using a visual question answering model

https://github.com/evelinehong/LBF

공식 코드

Learning by Fixing: Solving Math Word Problems with Weak Supervision

https://github.com/evolvinglmms-lab/egolife

공식 코드

EgoLife: Towards Egocentric Life Assistant

https://github.com/evolvinglmms-lab/lmms-eval

공식 코드

LLaVA-OneVision: Easy Visual Task Transfer

https://github.com/evolvinglmms-lab/longva

공식 코드

Long Context Transfer from Language to Vision

https://github.com/evrog/russian-qa-jeopardy

공식 코드

A Russian Jeopardy! Data Set for Question-Answering Systems

https://github.com/explainableml/clevr-x

공식 코드

CLEVR-X: A Visual Reasoning Dataset for Natural Language Explanations

https://github.com/explainableml/zs-a2t

공식 코드

Zero-shot Translation of Attention Patterns in VQA Models to Natural Language

https://github.com/eyeline-research/survey-video-diffusion

공식 코드

Survey of Video Diffusion Models: Foundations, Implementations, and Applications

https://github.com/ezelikman/STaR

공식 코드

STaR: Bootstrapping Reasoning With Reasoning

https://github.com/ezelikman/quiet-star

공식 코드

Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking

https://github.com/facebook/MemNN

공식 코드

End-To-End Memory Networks

https://github.com/facebook/bAbI-tasks

공식 코드

Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks

https://github.com/facebookresearch/BLINK

공식 코드

Efficient One-Pass End-to-End Entity Linking for Questions

https://github.com/facebookresearch/BLINK/tree/master/elq

공식 코드

Efficient One-Pass End-to-End Entity Linking for Questions

https://github.com/facebookresearch/CCQA

공식 코드

CCQA: A New Web-Scale Question Answering Dataset for Model Pre-Training

https://github.com/facebookresearch/DPR

공식 코드

Dense Passage Retrieval for Open-Domain Question Answering

https://github.com/facebookresearch/DrQA

공식 코드

Reading Wikipedia to Answer Open-Domain Questions

https://github.com/facebookresearch/ELI5

공식 코드

ELI5: Long Form Question Answering

https://github.com/facebookresearch/EgoVLPv2

공식 코드

EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone

https://github.com/facebookresearch/EmbodiedQA

공식 코드

Multi-Target Embodied Question Answering

https://github.com/facebookresearch/FiD

공식 코드

Distilling Knowledge from Reader to Retriever for Question Answering

https://github.com/facebookresearch/GENRE

공식 코드

Autoregressive Entity Retrieval

https://github.com/facebookresearch/KILT

공식 코드

KILT: a Benchmark for Knowledge Intensive Language Tasks

https://github.com/facebookresearch/LAMA

공식 코드

Language Models as Knowledge Bases?

https://github.com/facebookresearch/MLQA

공식 코드

MLQA: Evaluating Cross-lingual Extractive Question Answering

https://github.com/facebookresearch/PAQ

공식 코드

PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them

https://github.com/facebookresearch/QA-Overlap

공식 코드

Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasets

https://github.com/facebookresearch/Replica-Dataset

공식 코드

The Replica Dataset: A Digital Replica of Indoor Spaces

https://github.com/facebookresearch/SpanBERT

공식 코드

SpanBERT: Improving Pre-training by Representing and Predicting Spans

https://github.com/facebookresearch/UniK-QA

공식 코드

UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering

https://github.com/facebookresearch/UnsupervisedDecomposition

공식 코드

Unsupervised Question Decomposition for Question Answering

https://github.com/facebookresearch/UnsupervisedQA

공식 코드

Unsupervised Question Answering by Cloze Translation

https://github.com/facebookresearch/Zero-Shot-DST

공식 코드

Zero-Shot Dialogue State Tracking via Cross-Task Transfer

https://github.com/facebookresearch/aqa-study

공식 코드

On the Efficacy of Adversarial Data Collection for Question Answering: Results from a Large-Scale Randomized Study

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.