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
Konferenzbeitrag | Veröffentlicht | Englisch
Volltext vorhanden für diesen Nachweis
Autor
;
Abstract / Bemerkung
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.
Erscheinungsjahr
Titel des Konferenzbandes
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Seite
78-89
Konferenz
EMNLP
Konferenzort
Doha, Qatar
Konferenzdatum
2014-10-26 – 2014-10-28
PUB-ID

Zitieren

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. Doha, Qatar: ACL.
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.
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]
Volltext(e)
Access Level
OA Open Access
Zuletzt Hochgeladen
2016-09-16T06:06:42Z

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Suchen in

Google Scholar