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/diegoemilio01/sparql-generation-with-entity-pre-trained-gpt-for-kg-question-answering

공식 코드

SPARQL Generation with Entity Pre-trained GPT for KG Question Answering

https://github.com/digitalepidemiologylab/covid-twitter-bert

공식 코드

COVID-Twitter-BERT: A Natural Language Processing Model to Analyse COVID-19 Content on Twitter

https://github.com/digitalharborfoundation/rag-for-math-qa

공식 코드

Retrieval-augmented Generation to Improve Math Question-Answering: Trade-offs Between Groundedness and Human Preference

https://github.com/digitalphonetics/intrinsic-subgraph-generation-for-vqa

공식 코드

Intrinsic Subgraph Generation for Interpretable Graph based Visual Question Answering

https://github.com/din0s/ambig_lfqa

공식 코드

Model Analysis & Evaluation for Ambiguous Question Answering

https://github.com/dinghanshen/SWEM

공식 코드

Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms

https://github.com/dirtyharrylyl/hake-ava

공식 코드

Interacted Object Grounding in Spatio-Temporal Human-Object Interactions

https://github.com/disi-unibo-nlp/medgenie

공식 코드

To Generate or to Retrieve? On the Effectiveness of Artificial Contexts for Medical Open-Domain Question Answering

https://github.com/dki-lab/GrailQA

공식 코드

Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Bases

https://github.com/dki-lab/arcaneqa

공식 코드

ArcaneQA: Dynamic Program Induction and Contextualized Encoding for Knowledge Base Question Answering

https://github.com/dki-lab/pangu

공식 코드

Don't Generate, Discriminate: A Proposal for Grounding Language Models to Real-World Environments

https://github.com/dlion168/Listen-and-Speak-Fairly

공식 코드

Listen and Speak Fairly: A Study on Semantic Gender Bias in Speech Integrated Large Language Models

https://github.com/dlyuangod/tinygpt-v

공식 코드

TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones

https://github.com/dm2-nd/edmem

공식 코드

A Unified Encoder-Decoder Framework with Entity Memory

https://github.com/dmis-lab/bioasq-biobert

공식 코드

Pre-trained Language Model for Biomedical Question Answering

https://github.com/dmis-lab/bioasq8b

공식 코드

Transferability of Natural Language Inference to Biomedical Question Answering

https://github.com/dmis-lab/biobert

공식 코드

BioBERT: a pre-trained biomedical language representation model for biomedical text mining

https://github.com/dmis-lab/compact

공식 코드

CompAct: Compressing Retrieved Documents Actively for Question Answering

https://github.com/dmis-lab/covidAsk

공식 코드

Answering Questions on COVID-19 in Real-Time

https://github.com/dmis-lab/excord

공식 코드

Learn to Resolve Conversational Dependency: A Consistency Training Framework for Conversational Question Answering

https://github.com/dmis-lab/gener

공식 코드

Simple Questions Generate Named Entity Recognition Datasets

https://github.com/dmis-lab/liquid

공식 코드

LIQUID: A Framework for List Question Answering Dataset Generation

https://github.com/dmis-lab/olaph

공식 코드

OLAPH: Improving Factuality in Biomedical Long-form Question Answering

https://github.com/dmis-lab/position-bias

공식 코드

Look at the First Sentence: Position Bias in Question Answering

https://github.com/dmis-lab/rag2

공식 코드

Rationale-Guided Retrieval Augmented Generation for Medical Question Answering

https://github.com/dmis-lab/self-biorag

공식 코드

Improving Medical Reasoning through Retrieval and Self-Reflection with Retrieval-Augmented Large Language Models

https://github.com/dmis-lab/seqtagqa

공식 코드

Sequence tagging for biomedical extractive question answering

https://github.com/dmis-lab/temporalhead

공식 코드

Does Time Have Its Place? Temporal Heads: Where Language Models Recall Time-specific Information

https://github.com/dmis-lab/tour

공식 코드

Optimizing Test-Time Query Representations for Dense Retrieval

https://github.com/dmollaaliod/bioasq-synergy-public

공식 코드

Query-Focused Extractive Summarisation for Finding Ideal Answers to Biomedical and COVID-19 Questions

https://github.com/dmollaaliod/bioasq10b-public

공식 코드

Query-focused Extractive Summarisation for Biomedical and COVID-19 Complex Question Answering

https://github.com/doc-doc/NExT-QA

공식 코드

NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions

https://github.com/doc-doc/covgt

공식 코드

Contrastive Video Question Answering via Video Graph Transformer

https://github.com/doc-doc/hqga

공식 코드

Video as Conditional Graph Hierarchy for Multi-Granular Question Answering

https://github.com/doc-doc/next-gqa

공식 코드

Can I Trust Your Answer? Visually Grounded Video Question Answering

https://github.com/doc-doc/vRGV

공식 코드

Visual Relation Grounding in Videos

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