Employing web search query click logs for multi-domain spoken language understanding

Dilek Hakkani-Tür; Gokhan Tur; Larry Heck; Asli Celikyilmaz; Ashley Fidler; Dustin Hillard; Rukmini Iyer; Sarangarajan Parthasarathy

doi:10.1109/ASRU.2011.6163968

Employing web search query click logs for multi-domain spoken language understanding

Dilek Hakkani-Tür, Gokhan Tur, Larry Heck, Asli Celikyilmaz, Ashley Fidler, Dustin Hillard, Rukmini Iyer, Sarangarajan Parthasarathy

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Logs of user queries from a search engine (such as Bing or Google) together with the links clicked provide valuable implicit feedback to improve statistical spoken language understanding (SLU) models. In this work, we propose to enrich the existing classification feature set for domain detection with features computed using the click distribution over a set of clicked URLs from search query click logs (QCLs) of user utterances. Since the form of natural language utterances differs stylistically from that of keyword search queries, to be able to match natural language utterances with related search queries, we perform a syntax-based transformation of the original utterances, after filtering out domain-independent salient phrases. This approach results in significant improvements for domain detection, especially when detecting the domains of web-related user utterances.

Original language	English (US)
Title of host publication	2011 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2011, Proceedings
Pages	419-424
Number of pages	6
DOIs	https://doi.org/10.1109/ASRU.2011.6163968
State	Published - 2011
Externally published	Yes
Event	2011 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2011 - Waikoloa, HI, United States Duration: Dec 11 2011 → Dec 15 2011

Publication series

Name	2011 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2011, Proceedings

Conference

Conference	2011 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2011
Country/Territory	United States
City	Waikoloa, HI
Period	12/11/11 → 12/15/11

ASJC Scopus subject areas

Artificial Intelligence
Computer Vision and Pattern Recognition
Human-Computer Interaction

Online availability

10.1109/ASRU.2011.6163968

Library availability

Discover UIUC Full Text

Cite this

Hakkani-Tür, D., Tur, G., Heck, L., Celikyilmaz, A., Fidler, A., Hillard, D., Iyer, R., & Parthasarathy, S. (2011). Employing web search query click logs for multi-domain spoken language understanding. In 2011 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2011, Proceedings (pp. 419-424). Article 6163968 (2011 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2011, Proceedings). https://doi.org/10.1109/ASRU.2011.6163968

Employing web search query click logs for multi-domain spoken language understanding. / Hakkani-Tür, Dilek; Tur, Gokhan; Heck, Larry et al.
2011 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2011, Proceedings. 2011. p. 419-424 6163968 (2011 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2011, Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Hakkani-Tür, D, Tur, G, Heck, L, Celikyilmaz, A, Fidler, A, Hillard, D, Iyer, R & Parthasarathy, S 2011, Employing web search query click logs for multi-domain spoken language understanding. in 2011 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2011, Proceedings., 6163968, 2011 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2011, Proceedings, pp. 419-424, 2011 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2011, Waikoloa, HI, United States, 12/11/11. https://doi.org/10.1109/ASRU.2011.6163968

Hakkani-Tür D, Tur G, Heck L, Celikyilmaz A, Fidler A, Hillard D et al. Employing web search query click logs for multi-domain spoken language understanding. In 2011 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2011, Proceedings. 2011. p. 419-424. 6163968. (2011 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2011, Proceedings). doi: 10.1109/ASRU.2011.6163968

@inproceedings{2fd9b85345e94211b747ddaccdd8710a,

title = "Employing web search query click logs for multi-domain spoken language understanding",

abstract = "Logs of user queries from a search engine (such as Bing or Google) together with the links clicked provide valuable implicit feedback to improve statistical spoken language understanding (SLU) models. In this work, we propose to enrich the existing classification feature set for domain detection with features computed using the click distribution over a set of clicked URLs from search query click logs (QCLs) of user utterances. Since the form of natural language utterances differs stylistically from that of keyword search queries, to be able to match natural language utterances with related search queries, we perform a syntax-based transformation of the original utterances, after filtering out domain-independent salient phrases. This approach results in significant improvements for domain detection, especially when detecting the domains of web-related user utterances.",

author = "Dilek Hakkani-T{\"u}r and Gokhan Tur and Larry Heck and Asli Celikyilmaz and Ashley Fidler and Dustin Hillard and Rukmini Iyer and Sarangarajan Parthasarathy",

year = "2011",

doi = "10.1109/ASRU.2011.6163968",

language = "English (US)",

isbn = "9781467303675",

series = "2011 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2011, Proceedings",

pages = "419--424",

booktitle = "2011 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2011, Proceedings",

note = "2011 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2011 ; Conference date: 11-12-2011 Through 15-12-2011",

}

TY - GEN

T1 - Employing web search query click logs for multi-domain spoken language understanding

AU - Hakkani-Tür, Dilek

AU - Tur, Gokhan

AU - Heck, Larry

AU - Celikyilmaz, Asli

AU - Fidler, Ashley

AU - Hillard, Dustin

AU - Iyer, Rukmini

AU - Parthasarathy, Sarangarajan

PY - 2011

Y1 - 2011

N2 - Logs of user queries from a search engine (such as Bing or Google) together with the links clicked provide valuable implicit feedback to improve statistical spoken language understanding (SLU) models. In this work, we propose to enrich the existing classification feature set for domain detection with features computed using the click distribution over a set of clicked URLs from search query click logs (QCLs) of user utterances. Since the form of natural language utterances differs stylistically from that of keyword search queries, to be able to match natural language utterances with related search queries, we perform a syntax-based transformation of the original utterances, after filtering out domain-independent salient phrases. This approach results in significant improvements for domain detection, especially when detecting the domains of web-related user utterances.

AB - Logs of user queries from a search engine (such as Bing or Google) together with the links clicked provide valuable implicit feedback to improve statistical spoken language understanding (SLU) models. In this work, we propose to enrich the existing classification feature set for domain detection with features computed using the click distribution over a set of clicked URLs from search query click logs (QCLs) of user utterances. Since the form of natural language utterances differs stylistically from that of keyword search queries, to be able to match natural language utterances with related search queries, we perform a syntax-based transformation of the original utterances, after filtering out domain-independent salient phrases. This approach results in significant improvements for domain detection, especially when detecting the domains of web-related user utterances.

UR - http://www.scopus.com/inward/record.url?scp=84858994658&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84858994658&partnerID=8YFLogxK

U2 - 10.1109/ASRU.2011.6163968

DO - 10.1109/ASRU.2011.6163968

M3 - Conference contribution

AN - SCOPUS:84858994658

SN - 9781467303675

T3 - 2011 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2011, Proceedings

SP - 419

EP - 424

BT - 2011 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2011, Proceedings

T2 - 2011 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2011

Y2 - 11 December 2011 through 15 December 2011

ER -

Employing web search query click logs for multi-domain spoken language understanding

Abstract

Publication series

Conference

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this