Development of Dialogue Management System for Banking Services

Rapid increase in conversational AI and user chat data lead to intensive development of dialogue management systems (DMS) for various industries. Yet, for low-resource languages, such as Azerbaijani, very little research has been conducted. The main purpose of this work is to experiment with various...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Samir Rustamov, Aygul Bayramova, Emin Alasgarov
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	dialogue management systems low-resource language conversational artificial agent intent classification conversational chat-bot Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
Acceso en línea:	https://doaj.org/article/d05dbc042a2e40b69f9a3fcd60ab4bee
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:d05dbc042a2e40b69f9a3fcd60ab4bee
record_format	dspace
spelling	oai:doaj.org-article:d05dbc042a2e40b69f9a3fcd60ab4bee2021-11-25T16:42:42ZDevelopment of Dialogue Management System for Banking Services10.3390/app1122109952076-3417https://doaj.org/article/d05dbc042a2e40b69f9a3fcd60ab4bee2021-11-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/22/10995https://doaj.org/toc/2076-3417Rapid increase in conversational AI and user chat data lead to intensive development of dialogue management systems (DMS) for various industries. Yet, for low-resource languages, such as Azerbaijani, very little research has been conducted. The main purpose of this work is to experiment with various DMS pipeline set-ups to decide on the most appropriate natural language understanding and dialogue manager settings. In our project, we designed and evaluated different DMS pipelines with respect to the conversational text data obtained from one of the leading retail banks in Azerbaijan. In the work, the main two components of DMS—Natural language Understanding (NLU) and Dialogue Manager—have been investigated. In the first step of NLU, we utilized a language identification (LI) component for language detection. We investigated both built-in LI methods such as fastText and custom machine learning (ML) models trained on the domain-based dataset. The second step of the work was a comparison of the classic ML classifiers (logistic regression, neural networks, and SVM) and Dual Intent and Entity Transformer (DIET) architecture for user intention detection. In these experiments we used different combinations of feature extractors such as CountVectorizer, Term Frequency-Inverse Document Frequency (TF-IDF) Vectorizer, and word embeddings for both word and character n-gram based tokens. To extract important information from the text messages, Named Entity Extraction (NER) component was added to the pipeline. The best NER model was chosen among conditional random fields (CRF) tagger, deep neural networks (DNN), models and build in entity extraction component inside DIET architecture. Obtained entity tags fed to the Dialogue Management module as features. All NLU set-ups were followed by the Dialogue Management module that contains a Rule-based Policy to handle FAQs and chitchats as well as a Transformer Embedding Dialogue (TED) Policy to handle more complex and unexpected dialogue inputs. As a result, we suggest a DMS pipeline for a financial assistant, which is capable of identifying intentions, named entities, and a language of text followed by policies that allow generating a proper response (based on the designed dialogues) and suggesting the best next action.Samir RustamovAygul BayramovaEmin AlasgarovMDPI AGarticledialogue management systemslow-resource languageconversational artificial agentintent classificationconversational chat-botTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10995, p 10995 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	dialogue management systems low-resource language conversational artificial agent intent classification conversational chat-bot Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
spellingShingle	dialogue management systems low-resource language conversational artificial agent intent classification conversational chat-bot Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Samir Rustamov Aygul Bayramova Emin Alasgarov Development of Dialogue Management System for Banking Services
description	Rapid increase in conversational AI and user chat data lead to intensive development of dialogue management systems (DMS) for various industries. Yet, for low-resource languages, such as Azerbaijani, very little research has been conducted. The main purpose of this work is to experiment with various DMS pipeline set-ups to decide on the most appropriate natural language understanding and dialogue manager settings. In our project, we designed and evaluated different DMS pipelines with respect to the conversational text data obtained from one of the leading retail banks in Azerbaijan. In the work, the main two components of DMS—Natural language Understanding (NLU) and Dialogue Manager—have been investigated. In the first step of NLU, we utilized a language identification (LI) component for language detection. We investigated both built-in LI methods such as fastText and custom machine learning (ML) models trained on the domain-based dataset. The second step of the work was a comparison of the classic ML classifiers (logistic regression, neural networks, and SVM) and Dual Intent and Entity Transformer (DIET) architecture for user intention detection. In these experiments we used different combinations of feature extractors such as CountVectorizer, Term Frequency-Inverse Document Frequency (TF-IDF) Vectorizer, and word embeddings for both word and character n-gram based tokens. To extract important information from the text messages, Named Entity Extraction (NER) component was added to the pipeline. The best NER model was chosen among conditional random fields (CRF) tagger, deep neural networks (DNN), models and build in entity extraction component inside DIET architecture. Obtained entity tags fed to the Dialogue Management module as features. All NLU set-ups were followed by the Dialogue Management module that contains a Rule-based Policy to handle FAQs and chitchats as well as a Transformer Embedding Dialogue (TED) Policy to handle more complex and unexpected dialogue inputs. As a result, we suggest a DMS pipeline for a financial assistant, which is capable of identifying intentions, named entities, and a language of text followed by policies that allow generating a proper response (based on the designed dialogues) and suggesting the best next action.
format	article
author	Samir Rustamov Aygul Bayramova Emin Alasgarov
author_facet	Samir Rustamov Aygul Bayramova Emin Alasgarov
author_sort	Samir Rustamov
title	Development of Dialogue Management System for Banking Services
title_short	Development of Dialogue Management System for Banking Services
title_full	Development of Dialogue Management System for Banking Services
title_fullStr	Development of Dialogue Management System for Banking Services
title_full_unstemmed	Development of Dialogue Management System for Banking Services
title_sort	development of dialogue management system for banking services
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/d05dbc042a2e40b69f9a3fcd60ab4bee
work_keys_str_mv	AT samirrustamov developmentofdialoguemanagementsystemforbankingservices AT aygulbayramova developmentofdialoguemanagementsystemforbankingservices AT eminalasgarov developmentofdialoguemanagementsystemforbankingservices
_version_	1718413044530282496

Development of Dialogue Management System for Banking Services

Ejemplares similares