Authors:
Raffaele Piccini
and
Gerasimos Spanakis
Affiliation:
Department of Data Science and Knowledge Engineering, Maastricht University, Maastricht, 6200MD and Netherlands
Keyword(s):
Conversational Agents, Recurrent Neural Networks, Hierarchical Recurrent Encoder Decoder.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Artificial Intelligence
;
Knowledge Engineering and Ontology Development
;
Knowledge-Based Systems
;
Natural Language Processing
;
Pattern Recognition
;
Symbolic Systems
Abstract:
Conversational agents have begun to rise both in the academic (in terms of research) and commercial (in terms of applications) world. This paper investigates the task of building a non-goal driven conversational agent, using neural network generative models and analyzes how the conversation context is handled. It compares a simpler Encoder-Decoder with a Hierarchical Recurrent Encoder-Decoder architecture, which includes an additional module to model the context of the conversation using previous utterances information. We found that the hierarchical model was able to extract relevant context information and include them in the generation of the output. However, it performed worse (35-40%) than the simple Encoder-Decoder model regarding both grammatically correct output and meaningful response. Despite these results, experiments demonstrate how conversations about similar topics appear close to each other in the context space due to the increased frequency of specific topic-related w
ords, thus leaving promising directions for future research and how the context of a conversation can be exploited.
(More)