|
|
Machine-Learning Methods in Natural Language Processing
Vantuch, Marek ; Mrnuštík, Michal (referee) ; Otrusina, Lubomír (advisor)
Firstly, basic rules of tagging of the Czech language are described as well as problems connected to this field. Thereafter the focus of the thesis is put on the success rate of testing on the Czech corpus and at the same time trying to find the most suitable parameter values for using the features. After reaching a reasonable compromise between duration and accuracy, the value is then attempted to be improved using analysis of separate features and their eventual omission.
|
|
|
Automatic Identification of Paraphrases
Otrusina, Lubomír ; Schwarz, Petr (referee) ; Smrž, Pavel (advisor)
Automatic paraphrase discovery is an important task in natural language processing. Many systems use paraphrases for improve performance e.g. systems for question answering, information retrieval or document summarization. In this thesis, we explain basic concepts e.g. paraphrase or paraphrase pattern. Next we propose some methods for paraphrase discovery from various resources. Subsequently we propose an unsupervised method for discovering paraphrase from large plain text based on context and keywords between NE pairs. In the end we explain evaluation metods in paraphrase discovery area and then we evaluate our system and compare it with similar systems.
|
|
|
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.
|
|
|
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.
|
|
| |
|
|
Conversion of Science Articles to Plain Text
Matička, Jiří ; Dytrych, Jaroslav (referee) ; Otrusina, Lubomír (advisor)
Purpose of this bachelor's work is a research in the area of converting scientific articles in electronic form to plain text. Main topic is the group of problematic articles with certain possible components causing non-acceptable output. Many conversion tools were investigated and the one with the required and most accurate conversion was chosen. Second part of this thesis examines the problematic of automated conversion, including creation of conversion request, forward of all articles to conversion, the conversion itself, detection of finished conversions and delivery of all converted articles. To achieve this objective, a communication principle based on client/server in conjuction with Python scripts and available needed libraries were created. From the client's point of view, it is required only to create a list of articles for conversion and then call the appropriate function (create a request). Rest of the process is taken care of automatically and the resulting text files are available for the client in a folder set beforehand.
|
|
|
Using Explicit Semantic Analysis to Link in Multi-Lingual Document Collections
Žilka, Lukáš ; Otrusina, Lubomír (referee) ; Smrž, Pavel (advisor)
Udržování prolinkování dokumentů v ryhle rostoucích kolekcích je problematické. To je dále zvětšeno vícejazyčností těchto kolekcí. Navrhujeme použít Explicitní Sémantickou Analýzu k identifikaci relevantních dokumentů a linků napříč jazyky, bez použití strojového překladu. Navrhli jsme a implementovali několik přistupů v prototypu linkovacího systému. Evaluace byla provedena na Čínské, České, Anglické a Španělské Wikipedii. Diskutujeme evaluační metodologii pro linkovací systémy, a hodnotíme souhlasnost mezi odkazy v různých jazykoých verzích Wikipedie. Hodnotíme vlastnosti Explicitní Sémantické Analýzy důležité pro její praktické použití.
|
|
|
Actual Events Tracker
Odstrčilík, Martin ; Otrusina, Lubomír (referee) ; Kouřil, Jan (advisor)
The goal of the master thesis project was to develop an application for tracking of actual events in the surrounding area of the users. This application should allow the users to view events, create new events and add comments to existing ones. Beyond the implementation of developed application, this project deals with an analysis of the presented problem. The analysis includes a comparison with existing solutions and search for available technologies and frameworks applicable for implementation. Another part inside this work is description of the theory in behind of data classification that is internally used for event and comment analysis. This work also includes a design of appliction including design of user interface, software architecture, database, communication protocol and data classifiers. The main part of this project, the implementation, is described aftewards. At the end of this work, there is a summary of the whole process and also there are given some ideas about enhancing the application in the future.
|
|
|
Trie Structures for Large Text Data Processing
Rajčok, Andrej ; Otrusina, Lubomír (referee) ; Smrž, Pavel (advisor)
This study analyzes natural language processing with emphasis on morphological analysis of inflective languages and systems for named entity recognition. It analyzes effective pattern matching in dictionary by using succint structures and then analyzes practical implementation of succint structures. It describes design and implementation of named entity recognition system and morphological analyzer and compares and test their speed and effectiveness.
|
|
|
Adaptive RSS Reader
Luža, Jindřich ; Otrusina, Lubomír (referee) ; Smrž, Pavel (advisor)
Purpose of this balcheor thesis is posibility to enhance common RSS reader by extension, which allowing user filter RSS feed depends on that's classification by content to groups.There is discussed problems in common classification and in text classification. Forth, there is reveal teoretical aspect of RSS format, which is needed to be considered in implementation of RSS reader module and prototype of module. At last, testing of used classifier is stated here.
|
guest ::
