|
|
Question Answering over Structured Data
Birger, Mark ; Otrusina, Lubomír (referee) ; Smrž, Pavel (advisor)
Tato práce se zabývá problematikou odpovídání na otázky nad strukturovanými daty. Ve většině případů jsou strukturovaná data reprezentována pomocí propojených grafů, avšak ukrytí koncové struktury dát je podstatné pro využití podobných systémů jako součástí rozhraní s přirozeným jazykem. Odpovídající systém byl navržen a vyvíjen v rámci této práce. V porovnání s tradičními odpovídajícími systémy, které jsou založené na lingvistické analýze nebo statistických metodách, náš systém zkoumá poskytnutý graf a ve výsledků generuje sémantické vazby na základě vstupních párů otázka-odpověd'. Vyvíjený systém je nezávislý na struktuře dát, ale pro účely vyhodnocení jsme využili soubor dát z Wikidata a DBpedia. Kvalita výsledného systému a zkoumaného přístupu byla vyhodnocena s využitím připraveného datasetu a standartních metrik.
|
|
|
Brno Communication Agent
Jurkovič, Juraj ; Fajčík, Martin (referee) ; Smrž, Pavel (advisor)
The goal of this thesis is explore and subsequently apply techniques and technical solutions in development of information agents. Thesis primarily focuses on solving individual sub tasks using state of the art systems, interconnecting these systems, their adoption for specific domain and implementation of individual modules of communication agent system. User interface is based on multi-platform chat application Telegram. Information extraction from user input is executed by Dialogflow. Several external services are used for user request fulfillment. Elasticsearch is used for searching structured data. For answering open domain questions from free text we use R-net implementation. The resulting can have both ,its knowledge base and range of requests it can fulfill, easily extended and can be deployed to chat platform of choice.
|
|
|
Automatic Creation of Multi-Choice Tests for ISJ
Bambas, Tomáš ; Kouřil, Jan (referee) ; Smrž, Pavel (advisor)
This bachelor's thesis is concerned with a tests creation for the ISJ course. The aim of this work is the implementation of the application which serves for an automatic intelligent creation of tests relating to scripting languages Ruby and Python and regular expressions with support of an automatic evaluating of answers.
|
|
|
E-mail Client for OpenMoko
Krátký, Pavel ; Bartoň, Radek (referee) ; Smrž, Pavel (advisor)
Openmoko is a revolutionary Linux platform with an expanding community of developers. The goal of the project is to create a user-friendly email client programmed in Java and analyze the difficulties of application development on this platform. The thesis discusses possibilities of development of this kind of applications, especially those using SWT widget toolkit. JavaMail library which handles the electronic mail is described as well. In conclusion we demonstrate advantages and disadvantages of the created program. The outcome of this thesis is an email client designed for mobile Linux devices with touch control and an introduction to software development on the Openmoko platform.
|
|
|
Automatic Keyword Extraction in Czech
Gallovič, Ľubomír ; Otrusina, Lubomír (referee) ; Smrž, Pavel (advisor)
This thesis describes design, implementation and testing of application for automatic keyterm extraction from technical texts in czech language. Multiple algorithms for candidate selection, as well as various statistical and linguistic methods for score calculation were implemented. All of these algorithms were analyzed and compared, and best performing ones were chosen to be included in the final version of the program.
|
|
| |
|
|
Automatic Assignment of Student Projects in Python
Kyseľ, Juraj ; Škoda, Petr (referee) ; Smrž, Pavel (advisor)
This work focuses on automatic evaluation of student codes in Python programming language. Emphasis is placed primarily on feedback, to guide students in the correct Python code writing practices. In the practical part, the information obtained is used to design a system that alerts beginning programmers to errors and tries to teach them the right structures in the form of python idioms. Further, the thesis describes individual parts of the system, its inputs and outputs. As a case study, the system was put in place to support the teaching of the subject Scripting Languages at the FIT VUT in Brno in the academic year 2017/2018. The thesis summarizes the experience of this deployment and evaluates the advantages and problems of the processed solution.
|
|
|
Artificial Intelligence for Game Playing
Kučírek, Tomáš ; Šperka, Svatopluk (referee) ; Smrž, Pavel (advisor)
Arimaa is a strategic board game for two players. It was designed to be simple for human players and difficult for computers. The aim of this thesis is to design and implement the program with features of the artificial intelligence, which would be able to defeat human players. The implementation was realized in the three key parts: evaluation position, generation of moves and search. The program was run on the game server and defeated many bots as well as human players.
|
|
|
Semantic Annotation of Text
Dytrych, Jaroslav ; Svátek, Vojtěch (referee) ; Šaloun, Petr (referee) ; Smrž, Pavel (advisor)
This thesis deals with intelligent systems for support of the semantic annotation of text. It discusses the motivation for creation of such systems and state of the art in the areas of their usage. The thesis also describes newly proposed and realised annotation system which realizes advanced functions of semantic filtering and presentation of annotation suggestion alternatives in a unique way. The results of finished experiments clearly show the advantages of proposed solution. They also prove that the user interface of the annotation tools affects the annotation process. The optimisation of displayed information for the task of disambiguation of ambiguous entity names was done and proposed methods to speedup and increase of quality of the created annotations was experimentally evaluated. The comparison with the Protégé general tool has proven the benefits of created system for collaborative ontology creation which should be anchored in the text. In the conclusion, all achieved results are analysed and summarized.
|
|
|
Automatic Creation of Dictionaries from Translations
Svoboda, František ; Matějka, Pavel (referee) ; Smrž, Pavel (advisor)
Goal of this thesis is to implement system, capable of extracting bilingual dictionaries from parallel texts. Reader may find examples of how to obtain such documents and description of steps leading to successfull acquirement of desired information. Mainly statistical machine translation methods were examined and used for this purpose. Besides description of created system, short analysis of problems linked with the subject can be found as well as evaluation of results.
|
guest ::
