Impact of automatic comma prediction on POS/name tagging of speech

D. Hillard, Z. Huang, H. Ji, R. Grishman, D. Hakkani-Tur, M. Harper, M. Ostendorf, W. Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This work looks at the impact of automatically predicted commas on part-of-speech (POS) and name tagging of speech recognition transcripts of Mandarin broadcast news. There is a significant gain in both POS and name tagging accuracy due to using automatically predicted commas over sentence boundary prediction alone. One difference between Mandarin and English is that there are two types of commas, and experiments here show that, while they can be reliably distinguished in automatic prediction, the distinction does not give a clear benefit for POS or name tagging.

Original languageEnglish (US)
Title of host publication2006 IEEE ACL Spoken Language Technology Workshop, SLT 2006, Proceedings
Pages58-61
Number of pages4
DOIs
StatePublished - 2006
Event2006 IEEE ACL Spoken Language Technology Workshop, SLT 2006 - Palm Beach, Aruba
Duration: Dec 10 2006Dec 13 2006

Other

Other2006 IEEE ACL Spoken Language Technology Workshop, SLT 2006
CountryAruba
CityPalm Beach
Period12/10/0612/13/06

Fingerprint

Speech recognition
broadcast
news
Prediction
Comma
Part of Speech
Names
Tagging
experiment
Experiments
Speech Recognition
News Broadcasts
Experiment

Keywords

  • Natural language
  • Speech recognition

ASJC Scopus subject areas

  • Language and Linguistics
  • Human-Computer Interaction
  • Linguistics and Language

Cite this

Hillard, D., Huang, Z., Ji, H., Grishman, R., Hakkani-Tur, D., Harper, M., ... Wang, W. (2006). Impact of automatic comma prediction on POS/name tagging of speech. In 2006 IEEE ACL Spoken Language Technology Workshop, SLT 2006, Proceedings (pp. 58-61). [4123361] https://doi.org/10.1109/SLT.2006.326816

Impact of automatic comma prediction on POS/name tagging of speech. / Hillard, D.; Huang, Z.; Ji, H.; Grishman, R.; Hakkani-Tur, D.; Harper, M.; Ostendorf, M.; Wang, W.

2006 IEEE ACL Spoken Language Technology Workshop, SLT 2006, Proceedings. 2006. p. 58-61 4123361.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hillard, D, Huang, Z, Ji, H, Grishman, R, Hakkani-Tur, D, Harper, M, Ostendorf, M & Wang, W 2006, Impact of automatic comma prediction on POS/name tagging of speech. in 2006 IEEE ACL Spoken Language Technology Workshop, SLT 2006, Proceedings., 4123361, pp. 58-61, 2006 IEEE ACL Spoken Language Technology Workshop, SLT 2006, Palm Beach, Aruba, 12/10/06. https://doi.org/10.1109/SLT.2006.326816
Hillard D, Huang Z, Ji H, Grishman R, Hakkani-Tur D, Harper M et al. Impact of automatic comma prediction on POS/name tagging of speech. In 2006 IEEE ACL Spoken Language Technology Workshop, SLT 2006, Proceedings. 2006. p. 58-61. 4123361 https://doi.org/10.1109/SLT.2006.326816
Hillard, D. ; Huang, Z. ; Ji, H. ; Grishman, R. ; Hakkani-Tur, D. ; Harper, M. ; Ostendorf, M. ; Wang, W. / Impact of automatic comma prediction on POS/name tagging of speech. 2006 IEEE ACL Spoken Language Technology Workshop, SLT 2006, Proceedings. 2006. pp. 58-61
@inproceedings{e1b3cac8de974f2ebd0f65ac626d46dd,
title = "Impact of automatic comma prediction on POS/name tagging of speech",
abstract = "This work looks at the impact of automatically predicted commas on part-of-speech (POS) and name tagging of speech recognition transcripts of Mandarin broadcast news. There is a significant gain in both POS and name tagging accuracy due to using automatically predicted commas over sentence boundary prediction alone. One difference between Mandarin and English is that there are two types of commas, and experiments here show that, while they can be reliably distinguished in automatic prediction, the distinction does not give a clear benefit for POS or name tagging.",
keywords = "Natural language, Speech recognition",
author = "D. Hillard and Z. Huang and H. Ji and R. Grishman and D. Hakkani-Tur and M. Harper and M. Ostendorf and W. Wang",
year = "2006",
doi = "10.1109/SLT.2006.326816",
language = "English (US)",
isbn = "1424408733",
pages = "58--61",
booktitle = "2006 IEEE ACL Spoken Language Technology Workshop, SLT 2006, Proceedings",

}

TY - GEN

T1 - Impact of automatic comma prediction on POS/name tagging of speech

AU - Hillard, D.

AU - Huang, Z.

AU - Ji, H.

AU - Grishman, R.

AU - Hakkani-Tur, D.

AU - Harper, M.

AU - Ostendorf, M.

AU - Wang, W.

PY - 2006

Y1 - 2006

N2 - This work looks at the impact of automatically predicted commas on part-of-speech (POS) and name tagging of speech recognition transcripts of Mandarin broadcast news. There is a significant gain in both POS and name tagging accuracy due to using automatically predicted commas over sentence boundary prediction alone. One difference between Mandarin and English is that there are two types of commas, and experiments here show that, while they can be reliably distinguished in automatic prediction, the distinction does not give a clear benefit for POS or name tagging.

AB - This work looks at the impact of automatically predicted commas on part-of-speech (POS) and name tagging of speech recognition transcripts of Mandarin broadcast news. There is a significant gain in both POS and name tagging accuracy due to using automatically predicted commas over sentence boundary prediction alone. One difference between Mandarin and English is that there are two types of commas, and experiments here show that, while they can be reliably distinguished in automatic prediction, the distinction does not give a clear benefit for POS or name tagging.

KW - Natural language

KW - Speech recognition

UR - http://www.scopus.com/inward/record.url?scp=43849099968&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=43849099968&partnerID=8YFLogxK

U2 - 10.1109/SLT.2006.326816

DO - 10.1109/SLT.2006.326816

M3 - Conference contribution

AN - SCOPUS:43849099968

SN - 1424408733

SN - 9781424408733

SP - 58

EP - 61

BT - 2006 IEEE ACL Spoken Language Technology Workshop, SLT 2006, Proceedings

ER -