|
|
Development of trainable policies for spoken dialogue systems
Le, Thanh Cong ; Jurčíček, Filip (advisor) ; Peterek, Nino (referee)
Abstract Development of trainable policies for spoken dialogue systems Thanh Le In humanhuman interaction, speech is the most natural and effective manner of communication. Spoken Dialogue Systems (SDS) have been trying to bring that high level interaction to computer systems, so with SDS, you could talk to machines rather than learn to use mouse and keyboard for performing a task. However, as inaccuracy in speech recognition and inherent ambiguity in spoken language, the dialogue state (user's desire) can never be known with certainty, and therefore, building such a SDS is not trivial. Statistical approaches have been proposed to deal with these uncertainties by maintaining a probability distribution over every possible dialogue state. Based on these distributions, the system learns how to interact with users, somehow to achieve the final goal in the most effective manner. In Reinforcement Learning (RL), the learning process is understood as optimizing a policy of choosing action conditioned on the current belief state. Since the space of dialogue...
|
|
|
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
|
|
|
Approximative Bayes methods for belief monitoring in spoken dialogue systems
Marek, David ; Jurčíček, Filip (advisor) ; Žabokrtský, Zdeněk (referee)
The most important component of virtually any dialog system is a dialogue manager. The aim of the dialog manager is to propose an action (a continuation of the dialogue) given the last dialog state. The dialog state summarises all the past user input and the system input and ideally it includes all information necessary for natural progress in the dialog. For the dialog manager to work efficiently, it is important to model the probability distribution over all dialog states as precisely as possible. It is possible that the set of dialog states will be very large, so approximative methods usually must be used. In this thesis we will discuss an implementation of approximate Bayes methods for belief state monitoring. The result is a library for dialog state monitoring in real dialog systems. 1
|
|
| |
|
|
Consistency Checking of Relations Extracted from Text
Stejskal, Jakub ; Otrusina, Lubomír (referee) ; Smrž, Pavel (advisor)
This bachelor thesis is dedicated to mechanical techniques that are used in the natural language processing and information extraction from particular text. It is approaching the general methods that starting to process the raw text and it continues to the relations extraction from processed language constructs, moreover it provides options for the use of obtained relational data which can be seen for example in the project DBpedia. Another milestone of the described bachelor thesis is the design and implementation of an automated system for extracting information about entities, which do not have their own article on the English version of Wikipedia. Thesis also presents algorithms developed for the extraction of entities with their own name, the verification of the articles ‘existence of the extracted entities and finally the actual extraction of information about individual entities, which can be used during the information consistency checking. In the end, it can be seen the results and suggestions for further development of the created system.
|
|
|
Temporal Logics for a Man
Žilka, Lukáš ; Letko, Zdeněk (referee) ; Smrčka, Aleš (advisor)
The work deals with the automated translation of a natural language to temporal logic. Existing research attempts are summarized and built upon. For specificating the temporal properties a subset of English is introduced. The main contribution of the work is the proposed algorithm of translation of a property in the given language to LTL temporal logic, based on processing of and finding patterns in grammatical dependencies of The Stanford English Parser. Future research directions are discussed at the end.
|
|
|
Internet Robot for an Assistance of Calendar Scheduling
Klos, Jakub ; Očenášek, Pavel (referee) ; Smrčka, Aleš (advisor)
This bachelor thesis deals with the development of the internet robot for assistance of calendar scheduling. The robot and a user comunicate with a subset of English. User does not have to study special syntax of the orders which makes using of the robot-calendar much simplier. This easement is the main contribution of the work. This kind of control should help especially to the users with lesser amount of computer skills, for whom the special syntax-oriented-control might be difficult. The XMPP protocol is used for a comunication which is of instant messaging type. NLTK toolkit was used for natural language processing. The source code of the robot is completely programmed in Python programming language. The work also deals with possibilities of robot's further development.
|
|
|
Processing Czech in Python
Novotný, Zdeněk ; Schmidt, Marek (referee) ; Smrž, Pavel (advisor)
This bachorelor´s thesis presents some ways of Czech language processing. The first part contains a general destription of NLTK system. Some of aftermentioned functions were inspired by NLTK functions. There are described functions which attend to inflection and inflexion of various words class in Czech language. Next part is focused on processing of the text in Czech language in which are found and marked each sentences and other parts. Last part describes possibillity of tranformations rules application for each part of text. Results after rules application could be represented graphically.
|
|
|
Methods of Document Summarization on the Web
Belica, Michal ; Očenášek, Pavel (referee) ; Bartík, Vladimír (advisor)
The work deals with automatic summarization of documents in HTML format. As a language of web documents, Czech language has been chosen. The project is focused on algorithms of text summarization. The work also includes document preprocessing for summarization and conversion of text into representation suitable for summarization algorithms. General text mining is also briefly discussed but the project is mainly focused on the automatic document summarization. Two simple summarization algorithms are introduced. Then, the main attention is paid to an advanced algorithm that uses latent semantic analysis. Result of the work is a design and implementation of summarization module for Python language. Final part of the work contains evaluation of summaries generated by implemented summarization methods and their subjective comparison of the author.
|
|
|
Syntactic Analyzer for Czech Language
Beneš, Vojtěch ; Otrusina, Lubomír (referee) ; Kouřil, Jan (advisor)
Master’s thesis describes theoretical basics, solution design, and implementation of constituency (phrasal) parser for Czech language, which is based on a part of speech association into phrases. Created program works with manually built and annotated Czech sample corpus to generate probabilistic context free grammar within runtime machine learning. Parser implementation, based on extended CKY algorithm, then for the input Czech sentence decides if the sentence can be generated by the created grammar and for the positive cases constructs the most probable derivation tree. This result is then compared with the expected parse to evaluate constituency parser success rate.
|
guest ::
