AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Unsupervised Domain Adaptation on Reading Comprehension

Yu Cao, Meng Fang, Baosheng Yu, Joey Tianyi Zhou

AAAI 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Conditional distribution alignment · 38 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
apply CASe adaptation instead of direct zero-shot transferBERT base-uncased, CNN→SQuAD · SQuAD devEM: 18.97 -> 65.24Improved
apply CASe adaptation instead of direct zero-shot transferBERT base-uncased, DailyMail→CNN · CNN devEM: 77.22 -> 82.44Improved
apply CASe adaptation instead of direct zero-shot transferBERT base-uncased, CNN→NewsQA · NewsQA devEM: 9.38 -> 48.95Improved
apply CASe adaptation instead of direct zero-shot transferBERT base-uncased, SQuAD→CoQA · CoQA devEM: 29.58 -> 50.77Improved
add conditional discriminator conditioning on outputs (ablation)CASe, CNN→SQuAD · SQuAD devEM: 64.47 -> 65.24Improved
add conditional discriminator conditioning on outputs (ablation)CASe, DailyMail→CNN · CNN devEM: 82.26 -> 82.44Improved
add conditional discriminator conditioning on outputs (ablation)CASe, CNN→NewsQA · NewsQA devEM: 47.31 -> 48.95Improved
add conditional discriminator conditioning on outputs (ablation)CASe, SQuAD→CoQA · CoQA devEM: 50.25 -> 50.77Improved
add adversarial learning (ablation)CASe, CNN→SQuAD · SQuAD devEM: 65.05 -> 65.24Improved
add adversarial learning (ablation)CASe, DailyMail→CNN · CNN devEM: 81.21 -> 82.44Improved
add adversarial learning (ablation)CASe, CNN→NewsQA · NewsQA devEM: 47.89 -> 48.95Improved
add adversarial learning (ablation)CASe, SQuAD→CoQA · CoQA devEM: 49.05 -> 50.77Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy