Morphological segmentation for keyword spotting

Karthik Narasimhan; Damianos Karakos; Richard Schwartz; Stavros Tsakalidis; Regina Barzilay

doi:10.3115/v1/d14-1095

Morphological segmentation for keyword spotting

Karthik Narasimhan, Damianos Karakos, Richard Schwartz, Stavros Tsakalidis, Regina Barzilay

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

27 Scopus citations

Abstract

We explore the impact of morphological segmentation on keyword spotting (KWS). Despite potential benefits, stateof- The-art KWS systems do not use morphological information. In this paper, we augment a state-of-the-art KWS system with sub-word units derived from supervised and unsupervised morphological segmentations, and compare with phonetic and syllabic segmentations. Our experiments demonstrate that morphemes improve overall performance of KWS systems. Syllabic units, however, rival the performance of morphological units when used in KWS. By combining morphological, phonetic and syllabic segmentations, we demonstrate substantial performance gains.

Original language	English (US)
Title of host publication	EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
Publisher	Association for Computational Linguistics (ACL)
Pages	880-885
Number of pages	6
ISBN (Electronic)	9781937284961
DOIs	https://doi.org/10.3115/v1/d14-1095
State	Published - 2014
Externally published	Yes
Event	2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014 - Doha, Qatar Duration: Oct 25 2014 → Oct 29 2014

Publication series

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

Other

Other	2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014
Country/Territory	Qatar
City	Doha
Period	10/25/14 → 10/29/14

All Science Journal Classification (ASJC) codes

Computational Theory and Mathematics
Computer Vision and Pattern Recognition
Information Systems

Access to Document

10.3115/v1/d14-1095

Cite this

Narasimhan, K., Karakos, D., Schwartz, R., Tsakalidis, S., & Barzilay, R. (2014). Morphological segmentation for keyword spotting. In EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference (pp. 880-885). (EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference). Association for Computational Linguistics (ACL). https://doi.org/10.3115/v1/d14-1095

Narasimhan, Karthik ; Karakos, Damianos ; Schwartz, Richard et al. / Morphological segmentation for keyword spotting. EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2014. pp. 880-885 (EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference).

@inproceedings{af901d5bbed74512b8feb28a354dc3f1,

title = "Morphological segmentation for keyword spotting",

abstract = "We explore the impact of morphological segmentation on keyword spotting (KWS). Despite potential benefits, stateof- The-art KWS systems do not use morphological information. In this paper, we augment a state-of-the-art KWS system with sub-word units derived from supervised and unsupervised morphological segmentations, and compare with phonetic and syllabic segmentations. Our experiments demonstrate that morphemes improve overall performance of KWS systems. Syllabic units, however, rival the performance of morphological units when used in KWS. By combining morphological, phonetic and syllabic segmentations, we demonstrate substantial performance gains.",

author = "Karthik Narasimhan and Damianos Karakos and Richard Schwartz and Stavros Tsakalidis and Regina Barzilay",

note = "Publisher Copyright: {\textcopyright} 2014 Association for Computational Linguistics.; 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014 ; Conference date: 25-10-2014 Through 29-10-2014",

year = "2014",

doi = "10.3115/v1/d14-1095",

language = "English (US)",

series = "EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference",

publisher = "Association for Computational Linguistics (ACL)",

pages = "880--885",

booktitle = "EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference",

}

Narasimhan, K, Karakos, D, Schwartz, R, Tsakalidis, S & Barzilay, R 2014, Morphological segmentation for keyword spotting. 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. 880-885, 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014, Doha, Qatar, 10/25/14. https://doi.org/10.3115/v1/d14-1095

Morphological segmentation for keyword spotting. / Narasimhan, Karthik; Karakos, Damianos; Schwartz, Richard et al.
EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2014. p. 880-885 (EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference).

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

TY - GEN

T1 - Morphological segmentation for keyword spotting

AU - Narasimhan, Karthik

AU - Karakos, Damianos

AU - Schwartz, Richard

AU - Tsakalidis, Stavros

AU - Barzilay, Regina

PY - 2014

Y1 - 2014

N2 - We explore the impact of morphological segmentation on keyword spotting (KWS). Despite potential benefits, stateof- The-art KWS systems do not use morphological information. In this paper, we augment a state-of-the-art KWS system with sub-word units derived from supervised and unsupervised morphological segmentations, and compare with phonetic and syllabic segmentations. Our experiments demonstrate that morphemes improve overall performance of KWS systems. Syllabic units, however, rival the performance of morphological units when used in KWS. By combining morphological, phonetic and syllabic segmentations, we demonstrate substantial performance gains.

AB - We explore the impact of morphological segmentation on keyword spotting (KWS). Despite potential benefits, stateof- The-art KWS systems do not use morphological information. In this paper, we augment a state-of-the-art KWS system with sub-word units derived from supervised and unsupervised morphological segmentations, and compare with phonetic and syllabic segmentations. Our experiments demonstrate that morphemes improve overall performance of KWS systems. Syllabic units, however, rival the performance of morphological units when used in KWS. By combining morphological, phonetic and syllabic segmentations, we demonstrate substantial performance gains.

UR - http://www.scopus.com/inward/record.url?scp=84926052215&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84926052215&partnerID=8YFLogxK

U2 - 10.3115/v1/d14-1095

DO - 10.3115/v1/d14-1095

M3 - Conference contribution

AN - SCOPUS:84926052215

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

SP - 880

EP - 885

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

PB - Association for Computational Linguistics (ACL)

T2 - 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014

Y2 - 25 October 2014 through 29 October 2014

ER -

Narasimhan K, Karakos D, Schwartz R, Tsakalidis S, Barzilay R. Morphological segmentation for keyword spotting. In EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. Association for Computational Linguistics (ACL). 2014. p. 880-885. (EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference). doi: 10.3115/v1/d14-1095

Morphological segmentation for keyword spotting

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this