During the recent time periods, rapid growth within the field including dialogue systems has been visualized for making such systems automatically responsive towards human language. Conversational agents, specifically chatbots are purposefully approached for simulating interaction with humans. This is an enhancement within field of artificial intelligence (AI) as well as natural language processing also termed as NLP. Chatbots used for customer support systems utilize various machine learning models for example - retrieval learning, sequence-sequence learning, etc. The chatbots are utilized for interaction between humans and the systems through natural language in form of text, speech or a combination of both Such algorithms have seen advancements related to chatbots and dialogue systems while acting as a bridge of communication. These algorithms are applied on datasets acquired from customer support related to customer services of various companies. The experiments evaluate customer services through machine translation and text summarization in terms of word overlapping and similarities between chatbots responses and human responses to customer queries.

1.
Cluster-discovery of Twitter messages for event detection and trending
,”
S. B.
Kaleel
and
A.
Abhari
,
J. Comput. Sci.
,
2015
.
2.
Efficient estimation of word representations in vector space
,”
T.
Mikolov
,
K.
Chen
,
G.
Corrado
, and
J.
Dean
,
in 1st International Conference on Learning Representations, ICLR 2013 - Workshop Track Proceedings
,
2013
.
3.
Hate Speech and Abusive Language Classification using fastText
,”
G. B.
Herwanto
,
A. Maulida
Ningtyas
,
K. E.
Nugraha
, and
I. Nyoman Prayana
Trisna
,
in 2019 2nd International Seminar on Research of Information Technology and Intelligent Systems, ISRITI 2019
,
2019
.
4.
Word embeddings quantify 100 years of gender and ethnic stereotypes
,”
N.
Garg
,
L.
Schiebinger
,
D.
Jurafsky
, and
J.
Zou
,
Proc. Natl. Acad. Sci. U. S. A.
,
2018
.
5.
GloVe: Global vectors for word representation
,”
J.
Pennington
,
R.
Socher
, and
C. D.
Manning
,
in EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
,
2014
.
6.
Email data cleaning
,”
J.
Tang
,
H.
Li
,
Y.
Cao
, and
Z.
Tang
,
in Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
,
2005
.
7.
Reducing BERT Pre-Training Time from 3 Days to 76 Minutes
,”
Y.
You
,
J.
Li
,
J.
Hseu
,
X.
Song
,
J.
Demmel
, and
C.-J.
Hsieh
,
arXiv
,
2019
.
8.
NPCEditor: Creating virtual human dialogue using information retrieval techniques
,”
A.
Leuski
and
D.
Traum
,
AI Mag.
,
2011
.
9.
Filter, Rank, and Transfer the Knowledge: Learning to Chat
,”
S.
Jafarpour
and
C. J. C.
Burges
,
Learning
,
2010
.
10.
The probabilistic relevance framework: BM25 and beyond
,”
S.
Robertson
and
H.
Zaragoza
,
Found. Trends Inf. Retr.
,
2009
.
11.
Elasticsearch
,”
Int. J. Mod. Trends Eng. Res.
,
2018
.
12.
Adam: A method for stochastic optimization
,”
D. P.
Kingma
and
J. L.
Ba
,
in 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings
,
2015
.
13.
BLEUௗ: a Method for Automatic Evaluation of Machine Translation
,”
K.
Papineni
,
S.
Roukos
,
T.
Ward
, and
W.
Zhu
,
Comput. Linguist.
,
2002
.
14.
Rouge: A package for automatic evaluation of summaries
,”
C. Y.
Lin
,
Proc. Work. text Summ. branches out (WAS 2004
,
2004
.
15.
How not to evaluate your dialogue system: An empirical study of unsupervised evaluation metrics for dialogue response generation
,”
C. W.
Liu
,
R.
Lowe
,
I. V.
Serban
,
M.
Noseworthy
,
L.
Charlin
, and
J.
Pineau
,
in EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings
,
2016
.
16.
Towards an automatic turing test: Learning to evaluate dialogue responses
,”
R.
Lowe
,
N. A.
Gontier
,
M.
Noseworthy
,
Y.
Bengio
,
I. V.
Serban
, and
J.
Pineau
,
in ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
,
2017
.
This content is only available via PDF.
You do not currently have access to this content.