Neural relevance-aware query modeling for spoken document retrieval

Tien Hong Lo, Ying Wen Chen, Kuan Yu Chen, Hsin Min Wang, Berlin Chen

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

2 Citations (Scopus)

Abstract

Spoken document retrieval (SDR) is becoming a much-needed application due to that unprecedented volumes of audio-visual media have been made available in our daily life. As far as we are aware, most of the wide variety of SDR methods mainly focus on exploring robust indexing and effective retrieval methods to quantify the relevance degree between a pair of query and document. However, similar to information retrieval (IR), a fundamental challenge facing SDR is that a query is usually too short to convey a user's information need, such that a retrieval system cannot always achieve prospective efficacy when with the existing retrieval methods. In order to further boost retrieval performance, several studies turn their attention to reformulating the original query by leveraging an online pseudo-relevance feedback (PRF) process, which often comes at the price of taking significant time. Motivated by these observations, this paper presents a novel extension of the general line of SDR research and its contribution is at least two-fold. First, building on neural network-based techniques, we put forward a neural relevance-aware query modeling (NRM) framework, which is designed to not only infer a discriminative query language model automatically for a given query, but also get around the time-consuming PRF process. Second, the utility of the methods instantiated from our proposed framework and several widely-used retrieval methods are extensively analyzed and compared on a standard SDR task, which suggests the superiority of our methods.

Original languageEnglish
Title of host publication2017 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2017 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages466-473
Number of pages8
ISBN (Electronic)9781509047888
DOIs
Publication statusPublished - 2018 Jan 24
Event2017 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2017 - Okinawa, Japan
Duration: 2017 Dec 162017 Dec 20

Publication series

Name2017 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2017 - Proceedings
Volume2018-January

Conference

Conference2017 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2017
CountryJapan
CityOkinawa
Period17/12/1617/12/20

Fingerprint

Feedback
Query languages
Information retrieval
Neural networks

Keywords

  • neural networks
  • query language models
  • relevance feedback
  • Spoken document retrieval

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Human-Computer Interaction

Cite this

Lo, T. H., Chen, Y. W., Chen, K. Y., Wang, H. M., & Chen, B. (2018). Neural relevance-aware query modeling for spoken document retrieval. In 2017 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2017 - Proceedings (pp. 466-473). (2017 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2017 - Proceedings; Vol. 2018-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ASRU.2017.8268973

Neural relevance-aware query modeling for spoken document retrieval. / Lo, Tien Hong; Chen, Ying Wen; Chen, Kuan Yu; Wang, Hsin Min; Chen, Berlin.

2017 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2018. p. 466-473 (2017 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2017 - Proceedings; Vol. 2018-January).

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

Lo, TH, Chen, YW, Chen, KY, Wang, HM & Chen, B 2018, Neural relevance-aware query modeling for spoken document retrieval. in 2017 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2017 - Proceedings. 2017 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2017 - Proceedings, vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 466-473, 2017 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2017, Okinawa, Japan, 17/12/16. https://doi.org/10.1109/ASRU.2017.8268973
Lo TH, Chen YW, Chen KY, Wang HM, Chen B. Neural relevance-aware query modeling for spoken document retrieval. In 2017 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2018. p. 466-473. (2017 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2017 - Proceedings). https://doi.org/10.1109/ASRU.2017.8268973
Lo, Tien Hong ; Chen, Ying Wen ; Chen, Kuan Yu ; Wang, Hsin Min ; Chen, Berlin. / Neural relevance-aware query modeling for spoken document retrieval. 2017 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 466-473 (2017 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2017 - Proceedings).
@inproceedings{a83aabcdfc2644d9892965762c362a21,
title = "Neural relevance-aware query modeling for spoken document retrieval",
abstract = "Spoken document retrieval (SDR) is becoming a much-needed application due to that unprecedented volumes of audio-visual media have been made available in our daily life. As far as we are aware, most of the wide variety of SDR methods mainly focus on exploring robust indexing and effective retrieval methods to quantify the relevance degree between a pair of query and document. However, similar to information retrieval (IR), a fundamental challenge facing SDR is that a query is usually too short to convey a user's information need, such that a retrieval system cannot always achieve prospective efficacy when with the existing retrieval methods. In order to further boost retrieval performance, several studies turn their attention to reformulating the original query by leveraging an online pseudo-relevance feedback (PRF) process, which often comes at the price of taking significant time. Motivated by these observations, this paper presents a novel extension of the general line of SDR research and its contribution is at least two-fold. First, building on neural network-based techniques, we put forward a neural relevance-aware query modeling (NRM) framework, which is designed to not only infer a discriminative query language model automatically for a given query, but also get around the time-consuming PRF process. Second, the utility of the methods instantiated from our proposed framework and several widely-used retrieval methods are extensively analyzed and compared on a standard SDR task, which suggests the superiority of our methods.",
keywords = "neural networks, query language models, relevance feedback, Spoken document retrieval",
author = "Lo, {Tien Hong} and Chen, {Ying Wen} and Chen, {Kuan Yu} and Wang, {Hsin Min} and Berlin Chen",
year = "2018",
month = "1",
day = "24",
doi = "10.1109/ASRU.2017.8268973",
language = "English",
series = "2017 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2017 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "466--473",
booktitle = "2017 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2017 - Proceedings",

}

TY - GEN

T1 - Neural relevance-aware query modeling for spoken document retrieval

AU - Lo, Tien Hong

AU - Chen, Ying Wen

AU - Chen, Kuan Yu

AU - Wang, Hsin Min

AU - Chen, Berlin

PY - 2018/1/24

Y1 - 2018/1/24

N2 - Spoken document retrieval (SDR) is becoming a much-needed application due to that unprecedented volumes of audio-visual media have been made available in our daily life. As far as we are aware, most of the wide variety of SDR methods mainly focus on exploring robust indexing and effective retrieval methods to quantify the relevance degree between a pair of query and document. However, similar to information retrieval (IR), a fundamental challenge facing SDR is that a query is usually too short to convey a user's information need, such that a retrieval system cannot always achieve prospective efficacy when with the existing retrieval methods. In order to further boost retrieval performance, several studies turn their attention to reformulating the original query by leveraging an online pseudo-relevance feedback (PRF) process, which often comes at the price of taking significant time. Motivated by these observations, this paper presents a novel extension of the general line of SDR research and its contribution is at least two-fold. First, building on neural network-based techniques, we put forward a neural relevance-aware query modeling (NRM) framework, which is designed to not only infer a discriminative query language model automatically for a given query, but also get around the time-consuming PRF process. Second, the utility of the methods instantiated from our proposed framework and several widely-used retrieval methods are extensively analyzed and compared on a standard SDR task, which suggests the superiority of our methods.

AB - Spoken document retrieval (SDR) is becoming a much-needed application due to that unprecedented volumes of audio-visual media have been made available in our daily life. As far as we are aware, most of the wide variety of SDR methods mainly focus on exploring robust indexing and effective retrieval methods to quantify the relevance degree between a pair of query and document. However, similar to information retrieval (IR), a fundamental challenge facing SDR is that a query is usually too short to convey a user's information need, such that a retrieval system cannot always achieve prospective efficacy when with the existing retrieval methods. In order to further boost retrieval performance, several studies turn their attention to reformulating the original query by leveraging an online pseudo-relevance feedback (PRF) process, which often comes at the price of taking significant time. Motivated by these observations, this paper presents a novel extension of the general line of SDR research and its contribution is at least two-fold. First, building on neural network-based techniques, we put forward a neural relevance-aware query modeling (NRM) framework, which is designed to not only infer a discriminative query language model automatically for a given query, but also get around the time-consuming PRF process. Second, the utility of the methods instantiated from our proposed framework and several widely-used retrieval methods are extensively analyzed and compared on a standard SDR task, which suggests the superiority of our methods.

KW - neural networks

KW - query language models

KW - relevance feedback

KW - Spoken document retrieval

UR - http://www.scopus.com/inward/record.url?scp=85050614817&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050614817&partnerID=8YFLogxK

U2 - 10.1109/ASRU.2017.8268973

DO - 10.1109/ASRU.2017.8268973

M3 - Conference contribution

T3 - 2017 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2017 - Proceedings

SP - 466

EP - 473

BT - 2017 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2017 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -