Paper: Unsupervised Topic Identification By Integrating Linguistic And Visual Information Based On Hidden Markov Models

ACL ID P06-2097
Title Unsupervised Topic Identification By Integrating Linguistic And Visual Information Based On Hidden Markov Models
Venue Annual Meeting of the Association of Computational Linguistics
Session Poster Session
Year 2006
Authors

This paper presents an unsupervised topic identification method integrating linguis- tic and visual information based on Hid- den Markov Models (HMMs). We employ HMMs for topic identification, wherein a state corresponds to a topic and various features including linguistic, visual and audio information are observed. Our ex- periments on two kinds of cooking TV programs show the effectiveness of our proposed method.