Subword Lexical Chaining for Automatic Story Segmentation in Chinese Broadcast News

被引：0

作者：

Xie, Lei ^{[1
]}

Yang, Yulian ^{[1
]}

Zeng, Jia ^{[2
]}

机构：

[1] Northwestern Polytech Univ, Sch Comp Sci, Audio Speech & Language Proc Grp ASLP, Xian 710072, Peoples R China

[2] Hong Kong Baptist Univ, Dept Comp Sci, Hong Kong, Hong Kong, Peoples R China

来源：

ADVANCES IN MULTIMEDIA INFORMATION PROCESSING - PCM 2008, 9TH PACIFIC RIM CONFERENCE ON MULTIMEDIA | 2008年 / 5353卷

基金：

中国国家自然科学基金;

关键词：

Story segmentation; topic segmentation; spoken document retrieval; multimedia; Chinese;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

We present a subword lexical chaining approach to automatic story segmentation of Chinese broadcast news (BN). Conventional lexical chains link related words with cohesion (e.g. repetition of words) and high concentration points of starting and ending chains are indicative of story boundaries. However, inevitable speech recognition errors in BN transcripts may destroy the cohesiveness of words, resulting in word match failures. We show the robustness of Chinese subwords (characters and syllables) in lexical matching in errorful ASR transcripts. This motivates us to discover story boundaries on chains formed by character and syllable n-gram units. Experimental results on the TDT2 Mandarin corpus show that chaining by character unigram exhibits the best story segmentation performance with relative F-measure improvement of 6.06% over conventional word chaining. Integrations of multi-scales (words and subwords) exhibit further improvement. For example, fusion by voting from different scales achieves an F-measure gain of 9.04% over words.

引用

页码：248 / +

页数：3

共 50 条

[31] Automatic Segmentation of Broadcast News Audio using Self Similarity Matrix
Soni, Sapna
Ahmed, Imran
Kopparapu, Sunil Kumar
2014 INTERNATIONAL CONFERENCE FOR CONVERGENCE OF TECHNOLOGY (I2CT), 2014,
[32] Initial experiments on automatic story segmentation in Chinese spoken documents using lexical cohesion of extracted named entities
Li, Devon
Lo, Wai-Kit
Meng, Helen
CHINESE SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, 2006, 4274 : 693 - +
[33] MULTI-MODAL INFORMATION FUSION FOR NEWS STORY SEGMENTATION IN BROADCAST VIDEO
Feng, Bailan
Ding, Peng
Chen, Jiansong
Bai, Jinfeng
Xu, Su
Xu, Bo
2012 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2012, : 1417 - 1420
[34] Broadcast News Story Segmentation Using Conditional Random Fields and Multimodal Features
Wang, Xiaoxuan
Xie, Lei
Lu, Mimi
Ma, Bin
Chng, Eng Siong
Li, Haizhou
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2012, E95D (05) : 1206 - 1215
[35] Automatic transcription of Broadcast News
Chen, SS
Eide, E
Gales, MJF
Gopinath, RA
Kanvesky, D
Olsen, P
SPEECH COMMUNICATION, 2002, 37 (1-2) : 69 - 87
[36] AUTOMATIC COMPOSITION OF BROADCAST NEWS SUMMARIES USING RANK CLASSIFIERS TRAINED WITH ACOUSTIC AND LEXICAL FEATURES
Hasan, Taufiq
Abdelwahab, Mohammed
Parthasarathy, Srinivas
Busso, Carlos
Liu, Yang
2016 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING PROCEEDINGS, 2016, : 6080 - 6084
[37] Varying Input Segmentation for Story Boundary Detection in English, Arabic and Mandarin Broadcast News
Rosenberg, Andrew
Sharifi, Mehrbod
Hirschberg, Julia
INTERSPEECH 2007: 8TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION, VOLS 1-4, 2007, : 1745 - 1748
[38] Automatic Story Segmentation for TV News Video Using Multiple Modalities
Dumont, Emilie
Quenot, Georges
INTERNATIONAL JOURNAL OF DIGITAL MULTIMEDIA BROADCASTING, 2012, 2012
[39] Automatic Identification of Broadcast News Story Boundaries Using the Unification Method for Popular Nouns
Khalaf, Zainab Ali
Ping, Tan Tien
2013 FEDERATED CONFERENCE ON COMPUTER SCIENCE AND INFORMATION SYSTEMS (FEDCSIS), 2013, : 577 - 584
[40] Improving broadcast news segmentation processing
Boykin, S
Merlino, A
IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA COMPUTING AND SYSTEMS, PROCEEDINGS VOL 1, 1999, : 744 - 749

← 1 2 3 4 5 →