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

doi:10.1109/SLT.2006.326816

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

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference 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 language	English (US)
Title of host publication	2006 IEEE ACL Spoken Language Technology Workshop, SLT 2006, Proceedings
Pages	58-61
Number of pages	4
DOIs	https://doi.org/10.1109/SLT.2006.326816
State	Published - 2006
Event	2006 IEEE ACL Spoken Language Technology Workshop, SLT 2006 - Palm Beach, Aruba Duration: Dec 10 2006 → Dec 13 2006

Publication series

Name	2006 IEEE ACL Spoken Language Technology Workshop, SLT 2006, Proceedings

Other

Other	2006 IEEE ACL Spoken Language Technology Workshop, SLT 2006
Country/Territory	Aruba
City	Palm Beach
Period	12/10/06 → 12/13/06

Keywords

Natural language
Speech recognition

ASJC Scopus subject areas

Language and Linguistics
Human-Computer Interaction
Linguistics and Language

Access to Document

10.1109/SLT.2006.326816

Cite this

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 (pp. 58-61). [4123361] (2006 IEEE ACL Spoken Language Technology Workshop, SLT 2006, Proceedings). 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 (2006 IEEE ACL Spoken Language Technology Workshop, SLT 2006, Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference 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, 2006 IEEE ACL Spoken Language Technology Workshop, SLT 2006, Proceedings, 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

@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",

note = "Funding Information: M. Harper is also with CASL, University of Maryland, College Park, MD. This work was supported by DARPA grant MDA972-02-C-0038. Any opinions, findings and/or recommendations expressed in this paper are those of the authors and do not necessarily reflect the views of the funding agency.; 2006 IEEE ACL Spoken Language Technology Workshop, SLT 2006 ; Conference date: 10-12-2006 Through 13-12-2006",

year = "2006",

doi = "10.1109/SLT.2006.326816",

language = "English (US)",

isbn = "1424408733",

series = "2006 IEEE ACL Spoken Language Technology Workshop, SLT 2006, Proceedings",

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.

N1 - Funding Information: M. Harper is also with CASL, University of Maryland, College Park, MD. This work was supported by DARPA grant MDA972-02-C-0038. Any opinions, findings and/or recommendations expressed in this paper are those of the authors and do not necessarily reflect the views of the funding agency.

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

T3 - 2006 IEEE ACL Spoken Language Technology Workshop, SLT 2006, Proceedings

SP - 58

EP - 61

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

T2 - 2006 IEEE ACL Spoken Language Technology Workshop, SLT 2006

Y2 - 10 December 2006 through 13 December 2006

ER -

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

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this