Comparing word, character, and phoneme n-grams for subjective utterance recognition

被引：0
|
作者：
Wilson, Theresa [1 ]
Raaijmakers, Stephan [2 ]
机构：
[1] Univ Edinburgh, Sch Informat, Edinburgh, Midlothian, Scotland
[2] TNO Informat & Commun Technol, Delft, Netherlands
来源：
INTERSPEECH 2008: 9TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2008, VOLS 1-5 | 2008年
关键词：
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
In this paper, we compare the performance of classifiers trained using word n-grams, character n-grams, and phoneme n-grams for recognizing subjective utterances in multiparty conversation. We show that there is value in using very shallow linguistic representations, such as character n-grams, for recognizing subjective utterances, in particular, gains in the recall of subjective utterances.
引用
收藏
页码：1614 / +
页数：2
相关论文
共 50 条
  • [31] Using Word N-Grams as Features in Arabic Text Classification
    Al-Thubaity, Abdulmohsen
    Alhoshan, Muneera
    Hazzaa, Itisam
    SOFTWARE ENGINEERING, ARTIFICIAL INTELLIGENCE, NETWORKING AND PARALLEL/DISTRIBUTED COMPUTING, 2015, 569 : 35 - 43
  • [32] On the use of character n-grams as the only intrinsic evidence of plagiarism
    Imene Bensalem
    Paolo Rosso
    Salim Chikhi
    Language Resources and Evaluation, 2019, 53 : 363 - 396
  • [33] Algorithm for Updating n-Grams Word Dictionary for Web Classification
    Abidin, Taufik Fuadi
    Ferdhiana, Ridha
    2016 INTERNATIONAL CONFERENCE ON INFORMATICS AND COMPUTING (ICIC), 2016, : 432 - 436
  • [34] Algorithms for correcting recognition results using N-grams
    Manzhikov T.V.
    Slavin O.A.
    Faradjev I.A.
    Janiszewski I.M.
    Pattern Recognition and Image Analysis, 2017, 27 (4) : 832 - 837
  • [35] Learning Chinese Word Embeddings With Words and Subcharacter N-Grams
    Kang, Ruizhi
    Zhang, Hongjun
    Hao, Wenning
    Cheng, Kai
    Zhang, Guanglu
    IEEE ACCESS, 2019, 7 : 42987 - 42992
  • [36] Frequency Consolidation Among Word N-Grams A Practical Procedure
    Buerki, Andreas
    COMPUTATIONAL AND CORPUS-BASED PHRASEOLOGY, EUROPHRAS 2017, 2017, 10596 : 432 - 446
  • [37] Diacritics restoration based on word n-grams for Slovak texts
    Toth, Stefan
    Zaymus, Emanuel
    Duracik, Michal
    Hrkut, Patrik
    Mesko, Matej
    OPEN COMPUTER SCIENCE, 2021, 11 (01): : 180 - 189
  • [38] Comparing Simple Recurrent Networks and n-Grams in a Large Corpus
    Paul Rodriguez
    Applied Intelligence, 2003, 19 : 39 - 50
  • [39] Comparing simple recurrent networks and n-grams in a large corpus
    Rodriguez, P
    APPLIED INTELLIGENCE, 2003, 19 (1-2) : 39 - 50
  • [40] A Comparative Study of Likelihood Ratio Based Forensic Text Comparison Procedures: Multivariate Kernel Density with Lexical Features vs. Word N-grams vs. Character N-grams
    Ishihara, Shunichi
    2014 5TH CYBERCRIME AND TRUSTWORTHY COMPUTING CONFERENCE CTC, 2014, : 1 - 11
12345