AI Paper Atlas

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

Conversational Model Adaptation via KL Divergence Regularization

Juncen Li, Ping Luo, Fen Lin, Bo Chen

AAAI 2018 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Conditional distribution alignment · 6 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
KL-regularized adaptation instead of ft-REDft-RED · Target-domain test setBLEU: 7.71 -> 10.53Improved
KL-regularized adaptation instead of t-REDt-RED · Target-domain test setBLEU: 4.36 -> 10.53Improved
KL-regularized adaptation instead of c-REDc-RED · Target-domain test setBLEU: 1.35 -> 10.53Improved
combine source and target data (c-RED) instead of target only (t-RED)t-RED · Target-domain test setBLEU: 4.36 -> 1.35Hurt
combine source and target data (c-RED) instead of target only (t-RED)t-RED · Manual evaluationmean score: 0.318 -> 0.429Improved
pre-train on source then fine-tune (ft-RED) instead of target onlyt-RED · Target-domain test setBLEU: 4.36 -> 7.71Improved
KL-regularized adaptation instead of ft-REDft-RED · Manual evaluationmean score: 0.484 -> 0.530Improved
KL-regularized adaptation instead of c-REDc-RED · Manual evaluationmean score: 0.429 -> 0.530Improved
KL-regularized adaptation instead of t-REDt-RED · Manual evaluationBad(0) share: 71.3% -> 54.7%Improved

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