Leveraging effective query modeling techniques for speech recognition and summarization

Kuan Yu Chen, Shih Hung Liu, Berlin Chen, Ea Ee Jan, Hsin Min Wang, Wen Lian Hsu, Hsin Hsi Chen

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

8 Citations (Scopus)

Abstract

Statistical language modeling (LM) that purports to quantify the acceptability of a given piece of text has long been an interesting yet challenging research area. In particular, language modeling for information retrieval (IR) has enjoyed remarkable empirical success; one emerging stream of the LM approach for IR is to employ the pseudo-relevance feedback process to enhance the representation of an input query so as to improve retrieval effectiveness. This paper presents a continuation of such a general line of research and the main contribution is threefold. First, we propose a principled framework which can unify the relationships among several widely-used query modeling formulations. Second, on top of the successfully developed framework, we propose an extended query modeling formulation by incorporating critical query- specific information cues to guide the model estimation. Third, we further adopt and formalize such a framework to the speech recognition and summarization tasks. A series of empirical experiments reveal the feasibility of such an LM framework and the performance merits of the deduced models on these two tasks.

Original languageEnglish
Title of host publicationEMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages1474-1480
Number of pages7
ISBN (Electronic)9781937284961
Publication statusPublished - 2014 Jan 1
Event2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014 - Doha, Qatar
Duration: 2014 Oct 252014 Oct 29

Publication series

NameEMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference

Other

Other2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014
CountryQatar
CityDoha
Period14/10/2514/10/29

Fingerprint

Information retrieval
Speech recognition
Feedback
Experiments

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Vision and Pattern Recognition
  • Information Systems

Cite this

Chen, K. Y., Liu, S. H., Chen, B., Jan, E. E., Wang, H. M., Hsu, W. L., & Chen, H. H. (2014). Leveraging effective query modeling techniques for speech recognition and summarization. In EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference (pp. 1474-1480). (EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference). Association for Computational Linguistics (ACL).

Leveraging effective query modeling techniques for speech recognition and summarization. / Chen, Kuan Yu; Liu, Shih Hung; Chen, Berlin; Jan, Ea Ee; Wang, Hsin Min; Hsu, Wen Lian; Chen, Hsin Hsi.

EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2014. p. 1474-1480 (EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference).

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

Chen, KY, Liu, SH, Chen, B, Jan, EE, Wang, HM, Hsu, WL & Chen, HH 2014, Leveraging effective query modeling techniques for speech recognition and summarization. in EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference, Association for Computational Linguistics (ACL), pp. 1474-1480, 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014, Doha, Qatar, 14/10/25.
Chen KY, Liu SH, Chen B, Jan EE, Wang HM, Hsu WL et al. Leveraging effective query modeling techniques for speech recognition and summarization. In EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL). 2014. p. 1474-1480. (EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference).
Chen, Kuan Yu ; Liu, Shih Hung ; Chen, Berlin ; Jan, Ea Ee ; Wang, Hsin Min ; Hsu, Wen Lian ; Chen, Hsin Hsi. / Leveraging effective query modeling techniques for speech recognition and summarization. EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2014. pp. 1474-1480 (EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference).
@inproceedings{02d144aaa7584ece9103781e80b6869a,
title = "Leveraging effective query modeling techniques for speech recognition and summarization",
abstract = "Statistical language modeling (LM) that purports to quantify the acceptability of a given piece of text has long been an interesting yet challenging research area. In particular, language modeling for information retrieval (IR) has enjoyed remarkable empirical success; one emerging stream of the LM approach for IR is to employ the pseudo-relevance feedback process to enhance the representation of an input query so as to improve retrieval effectiveness. This paper presents a continuation of such a general line of research and the main contribution is threefold. First, we propose a principled framework which can unify the relationships among several widely-used query modeling formulations. Second, on top of the successfully developed framework, we propose an extended query modeling formulation by incorporating critical query- specific information cues to guide the model estimation. Third, we further adopt and formalize such a framework to the speech recognition and summarization tasks. A series of empirical experiments reveal the feasibility of such an LM framework and the performance merits of the deduced models on these two tasks.",
author = "Chen, {Kuan Yu} and Liu, {Shih Hung} and Berlin Chen and Jan, {Ea Ee} and Wang, {Hsin Min} and Hsu, {Wen Lian} and Chen, {Hsin Hsi}",
year = "2014",
month = "1",
day = "1",
language = "English",
series = "EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference",
publisher = "Association for Computational Linguistics (ACL)",
pages = "1474--1480",
booktitle = "EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference",

}

TY - GEN

T1 - Leveraging effective query modeling techniques for speech recognition and summarization

AU - Chen, Kuan Yu

AU - Liu, Shih Hung

AU - Chen, Berlin

AU - Jan, Ea Ee

AU - Wang, Hsin Min

AU - Hsu, Wen Lian

AU - Chen, Hsin Hsi

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Statistical language modeling (LM) that purports to quantify the acceptability of a given piece of text has long been an interesting yet challenging research area. In particular, language modeling for information retrieval (IR) has enjoyed remarkable empirical success; one emerging stream of the LM approach for IR is to employ the pseudo-relevance feedback process to enhance the representation of an input query so as to improve retrieval effectiveness. This paper presents a continuation of such a general line of research and the main contribution is threefold. First, we propose a principled framework which can unify the relationships among several widely-used query modeling formulations. Second, on top of the successfully developed framework, we propose an extended query modeling formulation by incorporating critical query- specific information cues to guide the model estimation. Third, we further adopt and formalize such a framework to the speech recognition and summarization tasks. A series of empirical experiments reveal the feasibility of such an LM framework and the performance merits of the deduced models on these two tasks.

AB - Statistical language modeling (LM) that purports to quantify the acceptability of a given piece of text has long been an interesting yet challenging research area. In particular, language modeling for information retrieval (IR) has enjoyed remarkable empirical success; one emerging stream of the LM approach for IR is to employ the pseudo-relevance feedback process to enhance the representation of an input query so as to improve retrieval effectiveness. This paper presents a continuation of such a general line of research and the main contribution is threefold. First, we propose a principled framework which can unify the relationships among several widely-used query modeling formulations. Second, on top of the successfully developed framework, we propose an extended query modeling formulation by incorporating critical query- specific information cues to guide the model estimation. Third, we further adopt and formalize such a framework to the speech recognition and summarization tasks. A series of empirical experiments reveal the feasibility of such an LM framework and the performance merits of the deduced models on these two tasks.

UR - http://www.scopus.com/inward/record.url?scp=84961345779&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84961345779&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84961345779

T3 - EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference

SP - 1474

EP - 1480

BT - EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference

PB - Association for Computational Linguistics (ACL)

ER -