Underspecification in Natural Language Understanding for Dialog Automation

John Chen, Srinivas Bangalore


Abstract
With the increasing number of communication platforms that offer variety of ways of connecting two interlocutors, there is a resurgence of chat-based dialog systems. These systems, typically known as chatbots have been successfully applied in a range of consumer and enterprise applications. A key technology in such chat-bots is robust natural language understanding (NLU) which can significantly influence and impact the efficacy of the conversation and ultimately the user-experience. While NLU is far from perfect, this paper illustrates the role of underspecification and its impact on successful dialog completion.
Anthology ID:
R17-1023
Volume:
Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017
Month:
September
Year:
2017
Address:
Varna, Bulgaria
Editors:
Ruslan Mitkov, Galia Angelova
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd.
Note:
Pages:
164–170
Language:
URL:
https://doi.org/10.26615/978-954-452-049-6_023
DOI:
10.26615/978-954-452-049-6_023
Bibkey:
Cite (ACL):
John Chen and Srinivas Bangalore. 2017. Underspecification in Natural Language Understanding for Dialog Automation. In Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017, pages 164–170, Varna, Bulgaria. INCOMA Ltd..
Cite (Informal):
Underspecification in Natural Language Understanding for Dialog Automation (Chen & Bangalore, RANLP 2017)
Copy Citation:
PDF:
https://doi.org/10.26615/978-954-452-049-6_023