Multi-modal feature integration for story boundary detection in broadcast news

Mi Mi Lu, Lei Xie, Zhong Hua Fu, Dong Mei Jiang, Yan Ning Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

10 Scopus citations

Abstract

This paper investigates how to integrate multi-modal features for story boundary detection in broadcast news. The detection problem is formulated as a classification task, i.e., classifying each candidate into boundary/non-boundary based on a set of features. We use a diverse collection of features from text, audio and video modalities: lexical features capturing the semantic shifts of news topics and audio/video features reflecting the editorial rules of broadcast news. We perform a comprehensive evaluation on boundary detection performance for six popular classifiers, including decision tree (DT), Bayesian network (BN), naive Bayesian (NB) classifier, multi-layer peceptron (MLP), support vector machines (SVM) and maximum entropy (ME) classifier. Results show that BN and DT can generally achieve superior performances over other classifiers and BN offers the best F1-measure. Analysis of BN and DT reveals important inter-feature dependencies and complementarities that contribute significantly to the performance gain.

Original languageEnglish
Title of host publication2010 7th International Symposium on Chinese Spoken Language Processing, ISCSLP 2010 - Proceedings
Pages420-425
Number of pages6
DOIs
StatePublished - 2010
Event2010 7th International Symposium on Chinese Spoken Language Processing, ISCSLP 2010 - Tainan, Taiwan, Province of China
Duration: 29 Nov 20103 Dec 2010

Publication series

Name2010 7th International Symposium on Chinese Spoken Language Processing, ISCSLP 2010 - Proceedings

Conference

Conference2010 7th International Symposium on Chinese Spoken Language Processing, ISCSLP 2010
Country/TerritoryTaiwan, Province of China
CityTainan
Period29/11/103/12/10

Keywords

  • Feature integration
  • Multi-modal
  • Story boundary detection
  • Story segmentation
  • Topic detection and tracking

Fingerprint

Dive into the research topics of 'Multi-modal feature integration for story boundary detection in broadcast news'. Together they form a unique fingerprint.

Cite this