Morphological Segmentation for Keyword Spotting
Name
Barzilay_Morphological segmentation.pdf
Size
116.82 KB
Format
Adobe PDF
Checksum (MD5)
fdcb99a421926e3b19208816c62abda5
Author(s)
Narasimhan, Karthik Rajagopal
Karakos, Damianos
Schwartz, Richard
Tsakalidis, Stavros
Barzilay, Regina
Date Issued
October 2014
Journal
Proceedings of the 2014 Conference on Empirical Methods on Natural Language Processing
Citation
Narasimhan, Karthik, Damianos Karakos, Richard Schwartz, Stavros Tsakalidis, and Regina Barzilay. "Morphological Segmentation for Keyword Spotting." 2014 Conference on Empirical Methods on Natural Language Processing (October 2014).
Version
Author's final manuscript
Abstract
We explore the impact of morphological segmentation on keyword spotting (KWS). Despite potential benefits, state-of-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.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
http://emnlp2014.org/papers.html
