This paper explains the working of the conversational AI models and their characteristic features. The primary objective of this paper is to let the readers know about what topical chats are and how they work. Topical chats have huge data/knowledge stored in them for making the conversation interactive and engaging with humans. The first-generation conversational AI models were simply focused on short task-oriented dialogs, such as telling jokes, the weather of the day, or playing songs. But now advanced models can have everyday smooth conversations. These models are built to understand different languages and their different accents. These models can identify whether the user is female/male/other, detect the change in the user’s emotion during the conversation and switch the topic of discussion accordingly. Building a conversational AI model has been a challenging task for researchers as well as the developers as they require deep knowledge in NLU, ASR, LM, Semantics, etc. Understanding human emotions and sentiments is a difficult task for an AI model. Recognizing the speech and giving a sensible response is challenging too. But nowadays AI models are so developed that they can even differentiate between good words and slang words.
| Published in | American Journal of Software Engineering and Applications (Volume 10, Issue 1) |
| DOI | 10.11648/j.ajsea.20211001.12 |
| Page(s) | 11-18 |
| Creative Commons |
This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited. |
| Copyright |
Copyright © The Author(s), 2021. Published by Science Publishing Group |
Topical Chat, NLU, ASR, Inappropriate Response Filtering, Conversational AI
| [1] | Hao Cheng Hao Fang Mari Ostendorf, 2019. A Dynamic Speaker Model for Conversational Interactions, Proceedings of NAACL-HLT 2019, pages 2772–2785. |
| [2] | Jurgita Kapočiūtė-Dzikienė, 2020. A Domain-Specific Generative Chatbot Trained from Little Data. Appl. Sci. 2020, 10, 2221; doi: 10.3390/app10072221. |
| [3] | Ashwin Ram, Rohit Prasad, Chandra Khatri, Anu Venkatesh, Raefer Gabriel, Qing Liu, Jeff Nunn, Behnam Hedayatnia, Ming Cheng, Ashish Nagar, Eric King, Kate Bland, Amanda Wartick, Yi Pan, Han Song, Sk Jayadevan, Gene Hwang, Art Pettigrue, 2018. Conversational AI: The Science Behind the Alexa Prize. arXiv: 1801.03604. |
| [4] | Minlie Huang, Xiaoyan Zhu, Jianfeng Gao, 2020. Challenges in Building Intelligent Open-domain Dialog Systems, arXiv: 1905.05709. |
| [5] | Soujanya Poria, Devamanyu Hazarika, Navonil Majumder, Gautam Naik, Erik Cambria, Rada Mihalcea, 2019. MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations arXiv: 1810.02508v6. |
| [6] | Pinkesh Badjatiya, Shashank Gupta, Manish Gupta, Vasudeva Varma, 2017 Deep Learning for Hate Speech Detection in Tweets, arXiv: 1706.00188v1. |
| [7] | Mohit Iyyer, Varun Manjunatha, Jordan Boyd-Graber, Hal Daume, 2015. Deep Unordered Composition Rivals Syntactic Methods for Text Classification. |
| [8] | Dawei Dai, Weimin Tan, Hong Zhan, 2017. Understanding the Feedforward Artificial Neural Network Model From the Perspective of Network Flow. |
| [9] | Tom Young, Devamanyu Hazarika, Soujanya Poria, Erik Cambria, 2018. Recent Trends in Deep Learning Based Natural Language Processing, arXiv: 1708.02709v8. |
| [10] | Ashwini Ann Varghese, Jacob P Cherian, Jubilant J Kizhakkethottam, 2015. Overview on emotionrecognition system, DOI: 10.1109/ICSNS.2015.7292443. |
| [11] | Pooja Withanage; Tharaka Liyanage; Naditha Deeyakaduwe; Eshan Dias; Samantha Thelijjagoda, 2018. Road Navigation System Using Automatic Speech Recognition (ASR) And Natural Language Processing (NLP), DOI: 10.1109/R10-HTC.2018.8629859. |
| [12] | Fenfei Guo, Angeliki Metallinou, Chandra Khatri, Anirudh Raju, Anu Venkatesh, Ashwin Ram, 2018. Topic-based Evaluation for Conversational Bots, arXiv: 1801.03622v1. |
| [13] | M. A. Anusuya, S. K. Katti, 2009. Speech Recognition by Machine: A Review, http://sites.google.com/site/ijcsis/ ISSN 1947-5500. |
| [14] | Xiaoping Sun, Xiangfeng Luo, Jin Liu, Xiaorui Jiang, Junsheng Zhang, 2015. Semantics in Deep Neural-Network Computing, doi: 10.1109/skg.2015.42. |
| [15] | David Doukhan; Jean Carrive; Felicien Vallet; Anthony Larcher; Sylvain Meignier, 2018. An Open-Source Speaker Gender Detection Framework for Monitoring Gender Equality, DOI: 10.1109/ICASSP.2018.8461471. |
| [16] | Cristiano Ialongo, 2016. Understanding the effect size and its measures, doi: 10.11613/BM.2016.015. |
| [17] | Christian Grimme, Mike Preuss, Lena Adam, and Heike Trautmann, 2017. Social Bots: Human-Like by Means of Human Control?, arXiv: 1706.07624v1. |
APA Style
Aishna Gupta, Anuska Rakshit. (2021). A Technical Survey on the Modeling of Topical Bot. American Journal of Software Engineering and Applications, 10(1), 11-18. https://doi.org/10.11648/j.ajsea.20211001.12
ACS Style
Aishna Gupta; Anuska Rakshit. A Technical Survey on the Modeling of Topical Bot. Am. J. Softw. Eng. Appl. 2021, 10(1), 11-18. doi: 10.11648/j.ajsea.20211001.12
AMA Style
Aishna Gupta, Anuska Rakshit. A Technical Survey on the Modeling of Topical Bot. Am J Softw Eng Appl. 2021;10(1):11-18. doi: 10.11648/j.ajsea.20211001.12
Share This Article
Twitter
Linked In
Facebook
Copy
Download@article{10.11648/j.ajsea.20211001.12,
author = {Aishna Gupta and Anuska Rakshit},
title = {A Technical Survey on the Modeling of Topical Bot},
journal = {American Journal of Software Engineering and Applications},
volume = {10},
number = {1},
pages = {11-18},
doi = {10.11648/j.ajsea.20211001.12},
url = {https://doi.org/10.11648/j.ajsea.20211001.12},
eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajsea.20211001.12},
abstract = {This paper explains the working of the conversational AI models and their characteristic features. The primary objective of this paper is to let the readers know about what topical chats are and how they work. Topical chats have huge data/knowledge stored in them for making the conversation interactive and engaging with humans. The first-generation conversational AI models were simply focused on short task-oriented dialogs, such as telling jokes, the weather of the day, or playing songs. But now advanced models can have everyday smooth conversations. These models are built to understand different languages and their different accents. These models can identify whether the user is female/male/other, detect the change in the user’s emotion during the conversation and switch the topic of discussion accordingly. Building a conversational AI model has been a challenging task for researchers as well as the developers as they require deep knowledge in NLU, ASR, LM, Semantics, etc. Understanding human emotions and sentiments is a difficult task for an AI model. Recognizing the speech and giving a sensible response is challenging too. But nowadays AI models are so developed that they can even differentiate between good words and slang words.},
year = {2021}
}
TY - JOUR T1 - A Technical Survey on the Modeling of Topical Bot AU - Aishna Gupta AU - Anuska Rakshit Y1 - 2021/07/16 PY - 2021 N1 - https://doi.org/10.11648/j.ajsea.20211001.12 DO - 10.11648/j.ajsea.20211001.12 T2 - American Journal of Software Engineering and Applications JF - American Journal of Software Engineering and Applications JO - American Journal of Software Engineering and Applications SP - 11 EP - 18 PB - Science Publishing Group SN - 2327-249X UR - https://doi.org/10.11648/j.ajsea.20211001.12 AB - This paper explains the working of the conversational AI models and their characteristic features. The primary objective of this paper is to let the readers know about what topical chats are and how they work. Topical chats have huge data/knowledge stored in them for making the conversation interactive and engaging with humans. The first-generation conversational AI models were simply focused on short task-oriented dialogs, such as telling jokes, the weather of the day, or playing songs. But now advanced models can have everyday smooth conversations. These models are built to understand different languages and their different accents. These models can identify whether the user is female/male/other, detect the change in the user’s emotion during the conversation and switch the topic of discussion accordingly. Building a conversational AI model has been a challenging task for researchers as well as the developers as they require deep knowledge in NLU, ASR, LM, Semantics, etc. Understanding human emotions and sentiments is a difficult task for an AI model. Recognizing the speech and giving a sensible response is challenging too. But nowadays AI models are so developed that they can even differentiate between good words and slang words. VL - 10 IS - 1 ER -
Email: