Strongly Incremental Repair Detection

Hough J, Purver M (2014)
In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). Doha, Qatar: ACL: 78-89.

Download
OA
Conference Paper | Published | English
Author
;
Abstract
We present STIR (STrongly Incremental Repair detection), a system that detects speech repairs and edit terms on transcripts incrementally with minimal latency. STIR uses information-theoretic measures from n-gram models as its principal decision features in a pipeline of classifiers detecting the different stages of repairs. Results on the Switchboard disfluency tagged corpus show utterance-final accuracy on a par with state-of-the-art incremental repair detection methods, but with better incremental accuracy, faster time-to-detection and less computational overhead. We evaluate its performance using incremental metrics and propose new repair processing evaluation standards.
Publishing Year
Conference
EMNLP
Location
Doha, Qatar
Conference Date
2014-10-26 – 2014-10-28
PUB-ID

Cite this

Hough J, Purver M. Strongly Incremental Repair Detection. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). Doha, Qatar: ACL; 2014: 78-89.
Hough, J., & Purver, M. (2014). Strongly Incremental Repair Detection. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), 78-89.
Hough, J., and Purver, M. (2014). “Strongly Incremental Repair Detection” in Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) (Doha, Qatar: ACL), 78-89.
Hough, J., & Purver, M., 2014. Strongly Incremental Repair Detection. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). Doha, Qatar: ACL, pp. 78-89.
J. Hough and M. Purver, “Strongly Incremental Repair Detection”, Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar: ACL, 2014, pp.78-89.
Hough, J., Purver, M.: Strongly Incremental Repair Detection. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). p. 78-89. ACL, Doha, Qatar (2014).
Hough, Julian, and Purver, Matthew. “Strongly Incremental Repair Detection”. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). Doha, Qatar: ACL, 2014. 78-89.
Main File(s)
Access Level
OA Open Access
Last Uploaded
2016-09-16T06:06:42Z

This data publication is cited in the following publications:
This publication cites the following data publications:

Export

0 Marked Publications

Open Data PUB

Search this title in

Google Scholar