On a Chat Bot Finding Answers with Optimal Rhetoric Representation

Boris Galitsky, Dmitry Ilvovsky


Abstract
We demo a chat bot with the focus on complex, multi-sentence questions that enforce what we call rhetoric agreement of answers with questions. Chat bot finds answers which are not only relevant by topic but also match the question by style, argumentation patterns, communication means, experience level and other attributes. The system achieves rhetoric agreement by learning pairs of discourse trees (DTs) for question (Q) and answer (A). We build a library of best answer DTs for most types of complex questions. To better recognize a valid rhetoric agreement between Q and A, DTs are extended with the labels for communicative actions. An algorithm for finding the best DT for an A, given a Q, is evaluated.
Anthology ID:
R17-1035
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:
253–259
Language:
URL:
https://doi.org/10.26615/978-954-452-049-6_035
DOI:
10.26615/978-954-452-049-6_035
Bibkey:
Cite (ACL):
Boris Galitsky and Dmitry Ilvovsky. 2017. On a Chat Bot Finding Answers with Optimal Rhetoric Representation. In Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017, pages 253–259, Varna, Bulgaria. INCOMA Ltd..
Cite (Informal):
On a Chat Bot Finding Answers with Optimal Rhetoric Representation (Galitsky & Ilvovsky, RANLP 2017)
Copy Citation:
PDF:
https://doi.org/10.26615/978-954-452-049-6_035