loading
Documents

Research.Publish.Connect.

Paper

Authors: Raffaele Piccini and Gerasimos Spanakis

Affiliation: Department of Data Science and Knowledge Engineering, Maastricht University, Maastricht, 6200MD, Netherlands

ISBN: 978-989-758-350-6

Keyword(s): Conversational Agents, Recurrent Neural Networks, Hierarchical Recurrent Encoder Decoder.

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 wo rds, thus leaving promising directions for future research and how the context of a conversation can be exploited. (More)

PDF ImageFull Text

Download
CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 34.237.76.91

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Piccini, R. and Spanakis, G. (2019). Exploring the Context of Recurrent Neural Network based Conversational Agents.In Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-350-6, pages 347-356. DOI: 10.5220/0007574203470356

@conference{icaart19,
author={Raffaele Piccini. and Gerasimos Spanakis.},
title={Exploring the Context of Recurrent Neural Network based Conversational Agents},
booktitle={Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2019},
pages={347-356},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007574203470356},
isbn={978-989-758-350-6},
}

TY - CONF

JO - Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Exploring the Context of Recurrent Neural Network based Conversational Agents
SN - 978-989-758-350-6
AU - Piccini, R.
AU - Spanakis, G.
PY - 2019
SP - 347
EP - 356
DO - 10.5220/0007574203470356

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.