Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

SCALABLE SENTIMENT FOR SEQUENCE-TO-SEQUENCE CHATBOT RESPONSE WITH PERFORMANCE ANALYSIS

Abstract: 

Conventional seq2seq chatbot models only try to find the sentences with the highest probabilities conditioned on the input sequences, without considering the sentiment of the output sentences. Some research works trying to modify the sentiment of the output sequences were reported. In this paper, we propose five models to scale or adjust the sentiment of the chatbot response: persona-based model, reinforcement learning, plug and play model, sentiment transformation network and cycleGAN, all based on the conventional seq2seq model. We also develop two evaluation metrics to estimate if the re- sponses are reasonable given the input. These metrics together with other two popularly used metrics were used to analyze the performance of the five proposed models on different aspects, and reinforcement learning and cycleGAN were shown to be very attractive. The evaluation metrics were also found to be well correlated with human evaluation.

up
0 users have voted:

Paper Details

Authors:
Chih-Wei Lee, Yau-Shian Wang, Tsung-Yuan Hsu, Kuan-Yu Chen, Hung-Yi Lee, Lin-shan Lee
Submitted On:
15 April 2018 - 4:05am
Short Link:
Type:
Whitepaper
Event:
Presenter's Name:
Lee, Chih Wei
Document Year:
2018
Cite

Document Files

lee.pdf

(73 downloads)

Subscribe

[1] Chih-Wei Lee, Yau-Shian Wang, Tsung-Yuan Hsu, Kuan-Yu Chen, Hung-Yi Lee, Lin-shan Lee, "SCALABLE SENTIMENT FOR SEQUENCE-TO-SEQUENCE CHATBOT RESPONSE WITH PERFORMANCE ANALYSIS", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2887. Accessed: Sep. 23, 2018.
@article{2887-18,
url = {http://sigport.org/2887},
author = {Chih-Wei Lee; Yau-Shian Wang; Tsung-Yuan Hsu; Kuan-Yu Chen; Hung-Yi Lee; Lin-shan Lee },
publisher = {IEEE SigPort},
title = {SCALABLE SENTIMENT FOR SEQUENCE-TO-SEQUENCE CHATBOT RESPONSE WITH PERFORMANCE ANALYSIS},
year = {2018} }
TY - EJOUR
T1 - SCALABLE SENTIMENT FOR SEQUENCE-TO-SEQUENCE CHATBOT RESPONSE WITH PERFORMANCE ANALYSIS
AU - Chih-Wei Lee; Yau-Shian Wang; Tsung-Yuan Hsu; Kuan-Yu Chen; Hung-Yi Lee; Lin-shan Lee
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2887
ER -
Chih-Wei Lee, Yau-Shian Wang, Tsung-Yuan Hsu, Kuan-Yu Chen, Hung-Yi Lee, Lin-shan Lee. (2018). SCALABLE SENTIMENT FOR SEQUENCE-TO-SEQUENCE CHATBOT RESPONSE WITH PERFORMANCE ANALYSIS. IEEE SigPort. http://sigport.org/2887
Chih-Wei Lee, Yau-Shian Wang, Tsung-Yuan Hsu, Kuan-Yu Chen, Hung-Yi Lee, Lin-shan Lee, 2018. SCALABLE SENTIMENT FOR SEQUENCE-TO-SEQUENCE CHATBOT RESPONSE WITH PERFORMANCE ANALYSIS. Available at: http://sigport.org/2887.
Chih-Wei Lee, Yau-Shian Wang, Tsung-Yuan Hsu, Kuan-Yu Chen, Hung-Yi Lee, Lin-shan Lee. (2018). "SCALABLE SENTIMENT FOR SEQUENCE-TO-SEQUENCE CHATBOT RESPONSE WITH PERFORMANCE ANALYSIS." Web.
1. Chih-Wei Lee, Yau-Shian Wang, Tsung-Yuan Hsu, Kuan-Yu Chen, Hung-Yi Lee, Lin-shan Lee. SCALABLE SENTIMENT FOR SEQUENCE-TO-SEQUENCE CHATBOT RESPONSE WITH PERFORMANCE ANALYSIS [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2887