Applying NLP to build a cold reading chatbot

Tracey, PJ, Saraee, MH ORCID: https://orcid.org/0000-0002-3283-1912 and Hughes, CJ ORCID: https://orcid.org/0000-0002-4468-6660 2020, Applying NLP to build a cold reading chatbot , in: European Conference on Natural Language Processing and Information Retrieval (ECNLPIR) 2020, 16th-18th September 2020, Online.

[img] PDF - Accepted Version
Restricted to Repository staff only

Download (233kB) | Request a copy
Official URL: http://www.ecnlpir.org/

Abstract

Chatbots are computer programs designed to simulate conversation by interacting with a human user. In this paper we present a chatbot framework designed specifically to aid prolonged grief disorder (PGD) sufferers by replicating the techniques performed during cold readings. Our initial framework performed an association rule analysis on transcripts of real-world cold reading performances, in order to generate the required data as used in traditional rules based chatbots. However due to the structure of cold readings the traditional approach was unable to determine a satisfactory set of rules. Therefore, in this paper we discuss the limitations of this approach and subsequently provide a generative solution using sequence-to-sequence modeling with long short-term memory. We demonstrate how our generative chatbot is therefore able to provide appropriate responses to the majority of inputs. However, as inappropriate responses can present a risk to sensitive PGD sufferers we suggest a final iteration of our chatbot which successfully adjusts to account for multi-turn conversations.

Item Type: Conference or Workshop Item (Paper)
Schools: Schools > School of Computing, Science and Engineering
Journal or Publication Title: European Conference on Natural Language Processing and Information Retrieval (ECNLPIR) 2020
Depositing User: Dr Chris Hughes
Date Deposited: 10 Nov 2020 13:18
Last Modified: 10 Nov 2020 13:19
URI: http://usir.salford.ac.uk/id/eprint/58507

Actions (login required)

Edit record (repository staff only) Edit record (repository staff only)

Downloads

Downloads per month over past year