GR Semicolon EN

Show simple item record

dc.contributor.author
Katsalis, Alkiviadis
en
dc.date.accessioned
2019-04-02T13:57:22Z
dc.date.available
2019-04-03T00:00:17Z
dc.date.issued
2019-04-02
dc.identifier.uri
https://repository.ihu.edu.gr//xmlui/handle/11544/29287
dc.rights
Default License
dc.subject
Machine learning
en
dc.subject
Natural language processing
en
dc.subject
Text mining
en
dc.title
Predicting User's Intent from Text using Machine Learning Methods
en
heal.type
masterThesis
en_US
heal.classification
Machine Learning, Natural Language Processing, Text mining
en
heal.language
en
en_US
heal.access
free
en_US
heal.license
http://creativecommons.org/licenses/by-nc/4.0
en_US
heal.recordProvider
School of Science and Technology, MSc in Data Science
en_US
heal.publicationDate
2019-04-01
heal.abstract
This dissertation was written as a part of the MSc in Data Science at the International Hellenic University. This thesis deals with a classification problem concerning prediction of users’ intent using Natural Language Processing (NLP) and machine learning techniques. Intent determination is a crucial part of Spoken Language Understanding systems. Recurrent Neural Networks are particularly effective in this task because they capture the order of the words in the text, which is one of its most essential characteristics. This work tackles this problem using pre-trained word embeddings and an LSTM neural model to extract the features for intent prediction. Other classifiers like SVM, Logistic Regression and MultiLayer Perceptron were tested too, without achieving the performance of the LSTM approach. Those methods are evaluated on the benchmark ATIS dataset. Compared to the current state of the art methods, the approach of this thesis achieves the best results, using a lightweight model containing a single LSTM layer which outperforms more complicated approaches that may also be slower or have overfitting issues. Specifically, it gave 0.44% absolute error reduction compared to the current state-of-the-art.
en
heal.advisorName
Diamantaras, Konstantinos
en
heal.committeeMemberName
Diamantaras, Konstantinos
en
heal.committeeMemberName
Berberidis, Christos
en
heal.committeeMemberName
Bassiliades, Nikolaos
en
heal.academicPublisher
IHU
en
heal.academicPublisherID
ihu
en_US


This item appears in the following Collection(s)

Show simple item record

Related Items