Task-oriented Conversational Agent Self-learning Based on Sentiment Analysis

One of the biggest issues in creating a task-oriented conversational agent with natural language processing based on machine learning comes from size and correctness of the training dataset. It could take months or even years of data collection and the resulting static resource may get soon out of date thus requiring a significant amount of work to supervise it. To overcome these difficulties, we implemented an algorithm with the ability of improving learning efficiency based on the emotions and reactions arising from the conversation between a user and the bot, automatically and in real time. To this end, we have studied an error function that, as in any closed loop control system, corrects the input to improve the output. The proposed method is based on both calibrating the interpretation given to the initial dataset and expanding the dictionary with new terms. Thanks to this innovative approach, the satisfaction of the interlocutors is higher if compared to algorithms with a static dataset or with semi-automatic self-learning rules.

[1]  David J. Miller,et al.  A Mixture of Experts Classifier with Learning Based on Both Labelled and Unlabelled Data , 1996, NIPS.

[2]  吴俊德.  Low-pass filter , 2008 .

[3]  Meng Zhang,et al.  Neural Network Methods for Natural Language Processing , 2017, Computational Linguistics.

[4]  Yan Zhou,et al.  Enhancing Supervised Learning with Unlabeled Data , 2000, ICML.

[5]  Tobias Scheffer,et al.  Learning to identify concise regular expressions that describe email campaigns , 2015, J. Mach. Learn. Res..

[6]  Avrim Blum,et al.  The Bottleneck , 2021, Monopsony Capitalism.

[7]  Ruslan Salakhutdinov,et al.  Semi-supervised mixture-of-experts classification , 2004, Fourth IEEE International Conference on Data Mining (ICDM'04).

[8]  K SoumyaGeorge,et al.  Text Classification by Augmenting Bag of Words (BOW) Representation with Co-occurrence Feature , 2014 .

[9]  Jonathan Crook,et al.  Sample selection bias in credit scoring models , 2003, J. Oper. Res. Soc..

[10]  James H. Martin,et al.  Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition , 2000 .

[11]  Rayid Ghani,et al.  Analyzing the effectiveness and applicability of co-training , 2000, CIKM '00.

[12]  Tong Zhang,et al.  The Value of Unlabeled Data for Classification Problems , 2000, ICML 2000.

[13]  Tom Fawcett,et al.  Robust Classification for Imprecise Environments , 2000, Machine Learning.

[14]  Michael I. Jordan,et al.  Learning from Incomplete Data , 1994 .

[15]  Haiyi Zhang,et al.  Naïve Bayes Text Classifier , 2007 .

[16]  Rong Jin,et al.  Understanding bag-of-words model: a statistical framework , 2010, Int. J. Mach. Learn. Cybern..

[17]  Eric Atwell,et al.  Chatbots: Are they Really Useful? , 2007, LDV Forum.

[18]  Jugal K. Kalita,et al.  Deep Learning applied to NLP , 2017, ArXiv.

[19]  Jason Weston,et al.  A unified architecture for natural language processing: deep neural networks with multitask learning , 2008, ICML '08.

[20]  Valeria Quochi,et al.  OpeNER Sentiment Lexicon Italian - LMF , 2016 .

[21]  M. Seeger.  Learning with labeled and unlabeled dataMatthias , 2001 .