SyntaViz: Visualizing Voice Queries through a Syntax-Driven Hierarchical Ontology

Md Iftekhar Tanveer, Ferhan Ture


Abstract
This paper describes SyntaViz, a visualization interface specifically designed for analyzing natural-language queries that were created by users of a voice-enabled product. SyntaViz provides a platform for browsing the ontology of user queries from a syntax-driven perspective, providing quick access to high-impact failure points of the existing intent understanding system and evidence for data-driven decisions in the development cycle. A case study on Xfinity X1 (a voice-enabled entertainment platform from Comcast) reveals that SyntaViz helps developers identify multiple action items in a short amount of time without any special training. SyntaViz has been open-sourced for the benefit of the community.
Anthology ID:
D18-2001
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
Month:
November
Year:
2018
Address:
Brussels, Belgium
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1–6
Language:
URL:
https://www.aclweb.org/anthology/D18-2001
DOI:
10.18653/v1/D18-2001
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/D18-2001.pdf