A topical VAEGAN-IHMM approach for automatic story segmentation.
Yu J, Peng H, Wang G, Shi N.
Yu J, et al.
Math Biosci Eng. 2024 Jul 16;21(7):6608-6630. doi: 10.3934/mbe.2024289.
Math Biosci Eng. 2024.
PMID: 39176411
Free article.
To better learn topical domain representation, we used a topical classifier to supervise the training process of VAEGAN. Based on the learned feature, a segmentor splits the document into shorter ones with different topics. ...Experimental results on the TDT2 corpus demons …
To better learn topical domain representation, we used a topical classifier to supervise the training process of VAEGAN. Based on the …