papers AI Learner
The Github is limit! Click to go to the new site.

Why Didn't You Listen to Me? Comparing User Control of Human-in-the-Loop Topic Models

2019-05-23
Varun Kumar, Alison Smith-Renner, Leah Findlater, Kevin Seppi, Jordan Boyd-Graber

Abstract

To address the lack of comparative evaluation of Human-in-the-Loop Topic Modeling (HLTM) systems, we implement and evaluate three contrasting HLTM approaches using simulation experiments. These approaches are based on previously proposed frameworks, including constraints and informed prior-based methods. User control is desired, so we propose a control metric to measure whether refinement operations are applied as users expect. Informed prior-based methods provide better control than constraints, but constraints yield higher quality topics.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1905.09864

PDF

http://arxiv.org/pdf/1905.09864


上一篇 Copy this Sentence

Comments

Content