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/facebookresearch/atlas

공식 코드

Atlas: Few-shot Learning with Retrieval Augmented Language Models

https://github.com/facebookresearch/bart_ls

공식 코드

Adapting Pretrained Text-to-Text Models for Long Text Sequences

https://github.com/facebookresearch/causalvqa

공식 코드

CausalVQA: A Physically Grounded Causal Reasoning Benchmark for Video Models

https://github.com/facebookresearch/concurrentqa

공식 코드

Reasoning over Public and Private Data in Retrieval-Based Systems

https://github.com/facebookresearch/contriever

공식 코드

Unsupervised Dense Information Retrieval with Contrastive Learning

https://github.com/facebookresearch/crag

공식 코드

CRAG -- Comprehensive RAG Benchmark

https://github.com/facebookresearch/daqa

공식 코드

Temporal Reasoning via Audio Question Answering

https://github.com/facebookresearch/dpr-scale

공식 코드

Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?

https://github.com/facebookresearch/dpr-scale/tree/main/spar

공식 코드

Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?

https://github.com/facebookresearch/dst-egqa

공식 코드

Continual Dialogue State Tracking via Example-Guided Question Answering

https://github.com/facebookresearch/egotom

공식 코드

EgoToM: Benchmarking Theory of Mind Reasoning from Egocentric Videos

https://github.com/facebookresearch/fastText

공식 코드

Fast Linear Model for Knowledge Graph Embeddings

https://github.com/facebookresearch/forwardgnn

공식 코드

Forward Learning of Graph Neural Networks

https://github.com/facebookresearch/habitat-sim

공식 코드

Habitat: A Platform for Embodied AI Research

https://github.com/facebookresearch/imvotenet

공식 코드

ImVoteNet: Boosting 3D Object Detection in Point Clouds with Image Votes

https://github.com/facebookresearch/llama

공식 코드

LLaMA: Open and Efficient Foundation Language Models

https://github.com/facebookresearch/metaicl

공식 코드

MetaICL: Learning to Learn In Context

https://github.com/facebookresearch/mmf/tree/master/projects/movie_mcan

공식 코드

MoVie: Revisiting Modulated Convolutions for Visual Counting and Beyond

https://github.com/facebookresearch/multihop_dense_retrieval

공식 코드

Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval

https://github.com/facebookresearch/multimodal_rewardbench

공식 코드

Multimodal RewardBench: Holistic Evaluation of Reward Models for Vision Language Models

https://github.com/facebookresearch/npm

공식 코드

Nonparametric Masked Language Modeling

https://github.com/facebookresearch/quip

공식 코드

Question Answering Infused Pre-training of General-Purpose Contextualized Representations

https://github.com/facebookresearch/reliable_vqa

공식 코드

Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly

https://github.com/facebookresearch/romqa

공식 코드

RoMQA: A Benchmark for Robust, Multi-evidence, Multi-answer Question Answering

https://github.com/facebookresearch/selective-vqa_ood

공식 코드

Improving Selective Visual Question Answering by Learning from Your Peers

https://github.com/facebookresearch/timelineqa

공식 코드

TimelineQA: A Benchmark for Question Answering over Timelines

https://github.com/facebookresearch/vilbert-multi-task

공식 코드

12-in-1: Multi-Task Vision and Language Representation Learning

https://github.com/facebookresearch/vip

공식 코드

VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training

https://github.com/facebookresearch/vjepa2

공식 코드

V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning

https://github.com/fairyshine/chain-of-tools

공식 코드

Chain-of-Tools: Utilizing Massive Unseen Tools in the CoT Reasoning of Frozen Language Models

https://github.com/fajri91/ffci

공식 코드

FFCI: A Framework for Interpretable Automatic Evaluation of Summarization

https://github.com/famma-bench/bench-script

공식 코드

FAMMA: A Benchmark for Financial Domain Multilingual Multimodal Question Answering

https://github.com/fanchenyou/HME-VideoQA

공식 코드

Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering

https://github.com/fangbufang/sal

공식 코드

Separate and Locate: Rethink the Text in Text-based Visual Question Answering

https://github.com/fangjun-li/roomspace

공식 코드

Reframing Spatial Reasoning Evaluation in Language Models: A Real-World Simulation Benchmark for Qualitative Reasoning

https://github.com/fangyihao/hgot

공식 코드

HGOT: Hierarchical Graph of Thoughts for Retrieval-Augmented In-Context Learning in Factuality Evaluation

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