Unsupervised Learning of Interpretable Dialog Models release_xfm3pnxoa5fz5g53gb5d62nnfq

by Dhiraj Madan, Dinesh Raghu, Gaurav Pandey, Sachindra Joshi

Released as a article .

2018  

Abstract

Recently several deep learning based models have been proposed for end-to-end learning of dialogs. While these models can be trained from data without the need for any additional annotations, it is hard to interpret them. On the other hand, there exist traditional state based dialog systems, where the states of the dialog are discrete and hence easy to interpret. However these states need to be handcrafted and annotated in the data. To achieve the best of both worlds, we propose Latent State Tracking Network (LSTN) using which we learn an interpretable model in unsupervised manner. The model defines a discrete latent variable at each turn of the conversation which can take a finite set of values. Since these discrete variables are not present in the training data, we use EM algorithm to train our model in unsupervised manner. In the experiments, we show that LSTN can help achieve interpretability in dialog models without much decrease in performance compared to end-to-end approaches.
In text/plain format

Archived Files and Locations

application/pdf  351.7 kB
file_cqh3642gzbevffjbn3gakzohfi
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2018-11-02
Version   v1
Language   en ?
arXiv  1811.01012v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 4c0fe391-b434-4793-9cee-39e010b8e622
API URL: JSON