Bridging the Language Gap: Topic Adaptation for Documents with Different Technicality

14th International Conference on Artificial Intelligence and Statistics

Shuang Hong Yang Steven P. Crain Hongyuan Zha

PID  :  117914

来源: CEUR

【 摘 要 】

The languagegap, for example between low literacy laypersons and highlytechnical ex pert documents, is a fundamental barrier for crossdomain knowledge transfer. This paper seeks to close the gap at the thematic level via topic adaptation, i.e., adjusting the top ical structures for crossdomain documents according to a domain factor such as techni cality. We present a probabilistic model for this purpose based on joint modeling of topic and technicality. The proposed LDA model explicitly encodes the interplay between topic and technicality hierarchies, providing an ef fective topiclevel bridge between lay and ex pert documents. We demonstrate the use fulness of LDA with an application to con