|
|
Information Extraction from Wikipedia
Jurišica, Rudolf ; Otrusina, Lubomír (referee) ; Smrž, Pavel (advisor)
The goal of this thesis is to reduce the number of unknown referenced entities in Czech Wikipedia articles. This has been achieved by using some existing solutions, created by the KNOT research group at FIT BUT, and then by creating a set of programs. These programs are automatically run every month, when a new version of Wikipedia is released. They will automatically add new names to the knowledge base, generate their derived forms, and edit the articles themselves directly on Wikipedia.
|
|
|
Deep Neural Networks Used for Customer Support Cases Analysis
Marušic, Marek ; Ryšavý, Ondřej (referee) ; Pluskal, Jan (advisor)
Umelá inteligencia je pozoruhodne populárna v dnešnej dobe, pretože si dokáže poradiť s rôznymi veľmi komplexnými úlohami v odvetviach ako napr. spracovanie obrazu, spracovanie zvuku, spracovanie prirodzeného jazyka a podobne. Keďže Red Hat doteraz už vyriešil obrovksé množstvo zákazníckych požiadavkov počas podpory rôznych produktov. Preto bola navrhnutá myšlienka použiť umelú inteligenciu práve na tieto dáta a docieliť tak zlepšenie a zrýchlenie procesu riešenia zákaznícky požiadavkov. V tejto práci sú popísané použité techniky na spracovanie týchto dát a úlohy, ktoré je možné riešiť pomocou hlbokých neurónových sietí. Taktiež sú v tejto práci popísane rôzne modely, ktoré boli vytvorené počas riešenia tejto práce a snažia sa adresovať rôzne úlohy. Ich výkony sú porovnané na spomínaných úlohách.
|
|
|
XMPP Robot with Natural Language Interface
Krygielová, Magdaléna ; Fapšo, Michal (referee) ; Schmidt, Marek (advisor)
This bachelors thesis describes an XMPP robot which communicates using natural language. It works as an interface for various services, especially for providing information about train and bus connections. This robot allows people using Jabber network to get the information about implemented services the way which is natural for them, without the need of filling forms or remembering command formats.
|
|
|
Automatic Evaluation of e-Learning Tests
Hort, Jan ; Fapšo, Michal (referee) ; Smrž, Pavel (advisor)
The thesis is dealing with research of automatic evaluation of e-learning tests. That technology is useful for domain of computer aided learning and e-learning and intelligent tutoring systems. This is extending possibility of online testing the student's knowledge. This thesis is also dealing with norms for learning and intelligent tutoring systems. Briefly introduce some project of domain of intelligent tutoring systems.
|
|
|
Text to Audio Alignment
Šíma, Tomáš ; Baskar, Murali Karthick (referee) ; Szőke, Igor (advisor)
The purpose of this work is to research existing text-to-speech aligning algorithms. We chose an implementation of one these algorithms, based on Hidden-Markov Joint-Sequence Models, and we explored its strengths, quirks and weaknesses. We explored whether it is possible to predict the alignment accuracy using probability values generated from Viterbi algorithm and the beam search value. Our testing data comes from the BBC as part of MGB Challenge 2015. This data creates, with its high content diversity, near perfect testing set to prove our algorithm is flexible and error independent.
|
|
|
Encyclopedia Expert
Krč, Martin ; Schmidt, Marek (referee) ; Smrž, Pavel (advisor)
This project focuses on a system that answers questions formulated in natural language. Firstly, the report discusses problems associated with question answering systems and some commonly employed approaches. Emphasis is laid on shallow methods, which do not require many linguistic resources. The second part describes our work on a system that answers factoid questions, utilizing Czech Wikipedia as a source of information. Answer extraction is partly based on specific features of Wikipedia and partly on pre-defined patterns. Results show that for answering simple questions, the system provides significant improvements in comparison with a standard search engine.
|
|
| |
|
|
An Automatic Configuration of Services of Operating System
Schiffer, Peter ; Peringer, Petr (referee) ; Smrčka, Aleš (advisor)
This Master thesis describes the configuration of operating systems and their capabilities. It introduces differences between configuration of different operating systems according to their specialization, and it introduces advanced configuration of operating systems with third-party applications. The practical part of the thesis is a design of a new computer language aimed at describing a configuration of an operating system and its services. Such a description is used to automatically configure system services by translating it to a sequence of configuration commands. An advantage of the language is its readability by a human, but its similarity with natural languages introduces a certain level of ambiguity. The proposed method of automatic generation of commands deals with the ambiguity by searching and selecting as least as possible destructive commands.
|
|
|
Unsupervised and Semi-Supervised Multilingual Learning for Resource-Poor Languages
Tran, Manh-Ke ; Zeman, Daniel (advisor) ; Vidová Hladká, Barbora (referee)
This thesis focuses on unsupervised morphological seg- mentation, the fundamental task in NLP which aims to break words into morphemes. I describe and re-implement a model proposed in Lee et al. (2011) and evaluate it on 4 languages. Moreover, I present a generative model that could use word representation as extra fea- tures. The word representations are leant in unsupervised manner using neural language model. The experiment shows that using extra features improves the performance of the unsupervised model.
|
|
|
Text to Audio Alignment
Šíma, Tomáš ; Baskar, Murali Karthick (referee) ; Szőke, Igor (advisor)
The purpose of this work is to research existing text-to-speech aligning algorithms. We chose an implementation of one these algorithms, based on Hidden-Markov Joint-Sequence Models, and we explored its strengths, quirks and weaknesses. We explored whether it is possible to predict the alignment accuracy using probability values generated from Viterbi algorithm and the beam search value. Our testing data comes from the BBC as part of MGB Challenge 2015. This data creates, with its high content diversity, near perfect testing set to prove our algorithm is flexible and error independent.
|
guest ::
