National Repository of Grey Literature 37 records found  1 - 10nextend  jump to record: Search took 0.00 seconds. 
Prediction of sports results using neural networks
Šipoš, Daniel ; Kuboň, David (advisor) ; Vidová Hladká, Barbora (referee)
This thesis focuses on creating models of two different types of neural network used for predicting results of selected football and tennis matches and comparing these two models in terms of their accuracy and potential profit, if we had bet on those games in an average betting agency. Compared types of neural networks are feed-forward and recurrent neural network. Predicted football matches consist of league matches of three European leagues. Specific feature of this thesis is tracking accuracy in predicting matches, where neither team is a clear favorite to win according to the bookmakers. 1
Předpovídání trendů akciového trhu z novinových článků
Serebryannikova, Anastasia ; Kuboň, Vladislav (advisor) ; Vidová Hladká, Barbora (referee)
In this work we made an attempt to predict the upwards/downwards movement of the S&P 500 index from the news articles published by Bloomberg and Reuters. We employed the SVM classifier and conducted multiple experiments aiming at understanding the shape of the data and the specifics of the task better. As a result, we established the common evaluation settings for all our subsequent experiments. After that we tried incorporating various features into the model and also replicated several approaches previously suggested in the literature. We were able to identify some non-trivial dependencies in the data which helped us achieve a high accuracy on the development set. However, none of the models that we built showed comparable performance on the test set. We have come to the conclusion that whereas some trends or patterns can be identified in a particular dataset, such findings are usually barely transferable to other data. The experiments that we conducted support the idea that the stock market is changing at random and a high quality of prediction may only be achieved on particular sets of data and under very special settings, but not for the task of stock market prediction in general. 1
Zkoumání úlohy univerzálního sémantického značkování pomocí neuronových sítí, řešením jiných úloh a vícejazyčným učením
Abdou, Mostafa ; Vidová Hladká, Barbora (advisor) ; Libovický, Jindřich (referee)
July 19, 2018 In this thesis we present an investigation of multi-task and transfer learning using the recently introduced task of semantic tagging. First we employ a number of natural language processing tasks as auxiliaries for semantic tag- ging. Secondly, going in the other direction, we employ seman- tic tagging as an auxiliary task for three di erent NLP tasks: Part-of-Speech Tagging, Universal Dependency parsing, and Natural Language Inference. We compare full neural network sharing, partial neural network sharing, and what we term the learning what to share setting where neg- ative transfer between tasks is less likely. Fi- nally, we investigate multi-lingual learning framed as a special case of multi-task learning. Our ndings show considerable improvements for most experiments, demonstrating a variety of cases where multi-task and transfer learning methods are bene cial. 1 References 2
Pronunciation Validation in Speech Therapy Application
Černý, Patrik ; Peterek, Nino (advisor) ; Vidová Hladká, Barbora (referee)
Title: Pronunciation Validation in Speech Therapy Application Author: Bc. Patrik Černý Institute: Institute of Formal and Applied Linguistics Supervisor: Mgr. Nino Peterek, Ph.D., Institute of Formal and Applied Linguistics Abstract: A goal of this thesis is to design, create and test speech validation method based on current speech recognition algorithms. Resulting software is a speech therapy application for sounds or words training with feedback about pronunciation accuracy. Speech validation is based on CMUSphinx tools and on inaccurate pronunciation generation (using phonetic dictionary). Records with accurate and inaccurate pronunciations has been collected for training and testing purposes. It has been shown, that this design is not appropriate. Thanks to the software design, application can be easily extended by techniques, that could improve validation efficiency. Keywords: speech validation, word recognition, dyslalia, speech therapy appli- cation
Automatic concordance extraction from the Internet
Macháček, Dominik ; Križ, Vincent (advisor) ; Vidová Hladká, Barbora (referee)
Concordances are sentences containing given target word. They are profitable research objects in all linguistics fields. A big amount of concordances is exploited during lexical desambiguation problem solving. Language corpora are not able to supply sufficient number of concordances of some English verbs. In this thesis we elaborate a design and implementation of a console application for automatic extraction of given number of English concordances. The application gets on its input a target word, a part-of-speech and a number of sentences. Consecutively it seeks out and extracts on the Internet desired number of English sentences containing a target word as given part-of-speech. We created also a Python library which allows a modification of the application to any arbitrary language. We published it on PyPI server. A part of a work is also a webpage allowing users to try out the application through web interface. 1
Sledování aktivovanosti objektů v textech
Václ, Jan ; Vidová Hladká, Barbora (advisor) ; Žabokrtský, Zdeněk (referee)
The notion of salience in the discourse analysis models how the activation of referred objects evolves in the flow of text. The salience algorithm was already defined and tested briefly in an earlier research, we present a reproduction of its results in a larger scale using data from the Prague Dependency Treebank 3.0. The results are then collected into an accessible shape and analyzed both in their visual and quantitative form in the context of the two main resources of the salience - coreference relations and topic-focus articulation. Furthermore, a possibility of modeling the salience degree by a machine learning algorithm (decision trees and random forest) is examined. Finally, attempts are made with using the salience information in the machine learning NLP task of document clustering visualization. Powered by TCPDF (www.tcpdf.org)
Assessing the impact of manual corrections in the Groningen Meaning Bank
Weck, Benno ; Lopatková, Markéta (advisor) ; Vidová Hladká, Barbora (referee)
The Groningen Meaning Bank (GMB) project develops a corpus with rich syntactic and semantic annotations. Annotations in GMB are generated semi-automatically and stem from two sources: (i) Initial annotations from a set of standard NLP tools, (ii) Corrections/refinements by human annotators. For example, on the part-of-speech level of annotation there are currently 18,000 of those corrections, so called Bits of Wisdom (BOWs). For applying this information to boost the NLP processing we experiment how to use the BOWs in retraining the part-of-speech tagger and found that it can be improved to correct up to 70% of identified errors within held-out data. Moreover an improved tagger helps to raise the performance of the parser. Preferring sentences with a high rate of verified tags in retraining has proven to be the most reliable way. With a simulated active learning experiment using Query-by-Uncertainty (QBU) and Query-by- Committee (QBC) we proved that selectively sampling sentences for retraining yields better results with less data needed than random selection. In an additional pilot study we found that a standard maximum-entropy part-of-speech tagger can be augmented so that it uses already known tags to enhance its tagging decisions on an entire sequence without retraining a new model first. Powered by...
Native Language Identification of L2 Speakers of Czech
Tydlitátová, Ludmila ; Hana, Jiří (advisor) ; Vidová Hladká, Barbora (referee)
Native Language Identification is the task of identifying an author's na- tive language based on their productions in a second language. The absolute majority of previous work has focused on English as the second language. In this thesis, we work with 3,715 essays written in Czech by non-native speakers. We use machine learning methods to determine whether an au- thors native language belongs to the Slavic language group. By training models with different feature and parameter settings, we were able to reach an accuracy of 78%. 1
Named Entity Normalization in Czech Texts
Kubát, Petr ; Vidová Hladká, Barbora (advisor) ; Popel, Martin (referee)
Named entities are collocations used to refer to real world objects in text. Named entity normalization is a process of generating the basic form for a given named entity. The thesis is focused on creating a rule- based procedure for named entity normalization in Czech texts. The process of designing individual rules is closely examined. Stress is laid on the fact that each rule is motivated by entities from real-world texts. Additionally, some aspects of Czech language syntax are analyzed in order to achieve the highest possible accuracy. Based on the theoretical description of the procedure, a normalization application is implemented, and its accuracy is evaluated by comparison with manually normalized entities. Together with already existing tools for automatic named entity recognition, it is possible to use this normalizer in other text processing tasks, such as machine translation, searching and categorization, etc. Powered by TCPDF (www.tcpdf.org)
Sledování aktivovanosti objektů v textech
Václ, Jan ; Vidová Hladká, Barbora (advisor) ; Novák, Michal (referee)
The notion of salience in the discourse analysis models how the activation of referred objects evolves in the flow of text. The salience algorithm was already defined and tested briefly in an earlier research, we present a reproduction of its results in a larger scale using data from the Prague Discourse Treebank 1.0. The results are then collected into an accessible shape and analyzed both in their visual and quantitative form in the context of the two main resources of the salience - coreference relations and topic-focus articulation. Finally, attempts are made with using the salience information in the machine learning NLP tasks of document clustering and topic modeling. Powered by TCPDF (www.tcpdf.org)

National Repository of Grey Literature : 37 records found   1 - 10nextend  jump to record:
Interested in being notified about new results for this query?
Subscribe to the RSS feed.