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/fanzhenliu/dagad

Graph Attention Networks

https://github.com/fastalgo/imagenet_resnet50_lamb

Large Batch Optimization for Deep Learning: Training BERT in 76 minutes

https://github.com/fatLime/Predict-Lung-Disease

ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases

https://github.com/fate-ubw/raglab

Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection

https://github.com/fatyin88/MCQA_project

MMM: Multi-stage Multi-task Learning for Multi-choice Reading Comprehension

https://github.com/fciannel/bert_fciannel

Attention Is All You Need

https://github.com/fcorencoret/dynamic-rn

A simple neural network module for relational reasoning

https://github.com/feifengwhu/question_attention

Attention on Attention: Architectures for Visual Question Answering (VQA)

https://github.com/feizc/Machine-Translation-Pytorch

Attention Is All You Need

https://github.com/felixSchober/ABSA-Transformer

Attention Is All You Need

https://github.com/felixgwu/FastFusionNet

Fast Reading Comprehension with ConvNets

https://github.com/few-shot-NER-benchmark/BaselineCode

RoBERTa: A Robustly Optimized BERT Pretraining Approach

https://github.com/fjiangai/mmapis

Attention Is All You Need

https://github.com/flagalpha/llama2-chinese

LLaMA: Open and Efficient Foundation Language Models

https://github.com/flairNLP/flair

Deep contextualized word representations

https://github.com/flaviagiammarino/time-gan-tensorflow

Time-series Transformer Generative Adversarial Networks

https://github.com/flexible-fl/flex-nlp

RoBERTa: A Robustly Optimized BERT Pretraining Approach

https://github.com/flxst/nerblackbox

Attention Is All You Need

https://github.com/flyliu2017/bert

Attention Is All You Need

https://github.com/flyliu2017/bert_modularized

Attention Is All You Need

https://github.com/fmu2/PyTorch-MAML

Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML

https://github.com/fongyk/graph-attention

Graph Attention Networks

https://github.com/for-ai/llm-profiling-toolkit

Holistic Evaluation of Language Models

https://github.com/formulamonks/llm-benchmarker-suite

Scaling Instruction-Finetuned Language Models

https://github.com/foundation-model-stack/fms-fsdp

PaLM: Scaling Language Modeling with Pathways

https://github.com/fra-mari/The-Karl-Marx-Press-Review

Attention Is All You Need

https://github.com/francescomontagna/NAQANet-PyTorch

DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs

https://github.com/frankcgq105/BERTCHEN

Attention Is All You Need

https://github.com/franknb/Self-attention-DCGAN

Attention Is All You Need

https://github.com/franknb/Text-Summarization

Attention Is All You Need

https://github.com/fransou/is-meta-learning-necessary

Strategies for Pre-training Graph Neural Networks

https://github.com/freedomintelligence/huatuogpt

LLaMA: Open and Efficient Foundation Language Models

https://github.com/frgfm/Holocron

Large Batch Optimization for Deep Learning: Training BERT in 76 minutes

https://github.com/fschmid56/efficientat_hear

HEAR: Holistic Evaluation of Audio Representations

https://github.com/fsoft-ai4code/codecapybara

LLaMA: Open and Efficient Foundation Language Models

https://github.com/fstahlberg/tensor2tensor

Attention Is All You Need

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