|
|
Typical Usage Patterns of English Verbs
Smejkalová, Lenka ; Holub, Martin (advisor) ; Lopatková, Markéta (referee)
Corpus Pattern Analysis (CPA) is a corpus-based method that explores typical usage patterns of verbs in a text corpus, and describes meaning of verbs by means of contextual preferences defined both syntactically and semantically [1]. CPA in conjuction with the British National Corpus (BNC) is currently used to create The Pattern Dictionary of English Verbs (PDEV) [1, 2]. The thesis describes the current status of the PDEV, presents a thorough analysis of available data on typical usage patterns and explores possible applications of the PDEV for automatic lexical analysis. In this thesis procedures usable in further PDEV development have been designed and implemented. The first of them automatically extracts arguments of verbs from an output of English syntactic analysis. The second one uses the extracted arguments to create lists of lexical units that realize semantic types. The last procedure uses these lists to automatically recognize typical usage patterns of verbs. The thesis also evaluates inter-annotator agreement, automatic extraction of verb arguments in/from English sentence, and effectiveness of the proposed procedures in the extraction of lexical units that realize semantic types and in automatic recognition of typical usage patterns.
|
|
|
Automatic construction of semantic networks
Kirschner, Martin ; Pecina, Pavel (advisor) ; Holub, Martin (referee)
Presented work explores the possibilities of automatic construction and expansion of semantic networks with use of machine learning methods. The main focus is put on the feature retrieving procedure for the data set. The work presents a robust method of semantic relation retrieval, based on distributional hypothesis and trained on the data from Czech WordNet. We also show the first results for czech language in this area of research. Part of the thesis is also a set of software for processing and evaluating of input data and a overview and discussion about its results on real-world data. The resulting tools can process data of amount in orders of hundreds of millions of words. The research part of the thesis used Czech morphologicaly and syntacticaly annotated data, but the methods are not language dependent.
|
|
|
Syntax in methods for information retrieval
Kravalová, Jana ; Pecina, Pavel (advisor) ; Holub, Martin (referee)
In the last years, application of language modeling in information retrieval has been studied quite extensively. Although language models of any type can be used with this approach, only traditional n-gram models based on surface word order have been employed and described in published experiments (often only unigram language models). The goal of this thesis is to design, implement, and evaluate (on Czech data) a method which would extend a language model with syntactic information, automatically obtained from documents and queries. We attempt to incorporate syntactic information into language models and experimentally compare this approach with unigram and bigram model based on surface word order. We also empirically compare methods for smoothing, stemming and lemmatization, effectiveness of using stopwords and pseudo relevance feedback. We perform a detailed analysis of these retrieval methods and describe their performance in detail.
|
|
|
Combining text-based and vision-based semantics
Tran, Binh Giang ; Holub, Martin (advisor) ; Straková, Jana (referee)
Learning and representing semantics is one of the most important tasks that significantly contribute to some growing areas, as successful stories in the recent survey of Turney and Pantel (2010). In this thesis, we present an in- novative (and first) framework for creating a multimodal distributional semantic model from state of the art text-and image-based semantic models. We evaluate this multimodal semantic model on simulating similarity judgements, concept clustering and the newly introduced BLESS benchmark. We also propose an effective algorithm, namely Parameter Estimation, to integrate text- and image- based features in order to have a robust multimodal system. By experiments, we show that our technique is very promising. Across all experiments, our best multimodal model claims the first position. By relatively comparing with other text-based models, we are justified to affirm that our model can stay in the top line with other state of the art models. We explore various types of visual features including SIFT and other color SIFT channels in order to have prelim- inary insights about how computer-vision techniques should be applied in the natural language processing domain. Importantly, in this thesis, we show evi- dences that adding visual features (as the perceptual information coming from...
|
|
|
Automatic construction of semantic networks
Kirschner, Martin ; Pecina, Pavel (advisor) ; Holub, Martin (referee)
Presented work explores the possibilities of automatic construction and expansion of semantic networks with use of machine learning methods. The main focus is put on the feature retrieving procedure for the data set. The work presents a method of semantic relation retrieval, based on distributional hypothesis and trained on the data from Czech WordNet. We also show the first results for Czech language in this area of research. Part of the thesis is also a set of software for processing and evaluating of input data and a overview and discussion about its results on real-world data. The resulting tools can process data of amount in orders of hundreds of millions of words. The research part of the thesis used Czech morphologically and syntactically annotated data, but the methods are not language dependent.
|
|
|
Universal Full-Text Index
Švantner, Marek ; Holub, Martin (advisor) ; Skopal, Tomáš (referee)
This diploma thesis deals with the design and implementation of a highly efficient universal index of textual documents. Universal stands for an opportunity to configure structures of index records and methods of the index data processing (without recompiling an application). Furthermore, it means that the index library can be used even for other purposes, for example to implement a thesaurus, to represent bibliographic relationships or even for generic representation of a specific class of functions in other areas than documentographic systems. The index is implemented using the dynamic inverted file which can be efficiently updated without need of the data structure rebuilding. Specific issue is on-line index compression and failure recovery via the transactional log. It is shown that the amortized complexity of the data structure is linear. This fact is afterwards experimentally verified. Other experiments address the compression methods and the impact of the data structure parameters on its efficiency. The diploma thesis contains the implementation of the universal index in C/C++. It has been tested in the Linux and Windows XP environments.
|
|
|
Automatic suggestion of illustrative images
Odcházel, Ondřej ; Pecina, Pavel (advisor) ; Holub, Martin (referee)
The objective of this thesis is to implement a web application designed for recommendation of stock photos. The application gets the input from newspaper articles in Czech or English and, based on the text itself, suggests appropriate stock photos. The implemented application also searches images according to visual similarity. The thesis deals with theoretical aspects of keywords extraction and language of text detection. Further it analyzes possibilities of efficient search for similar vectors that are used in the search component for visually similar images. It also describes the possibilities in development of modern web frontend and backend. The quality of algorithm for recommending stock photos is tested on users. Powered by TCPDF (www.tcpdf.org)
|
|
|
Clusters of closely related documents
Diviš, Jiří ; Holub, Martin (advisor) ; Húsek, Dušan (referee)
This thesis focuses on automatic searching for clusters of topically similar texts in large text collection. We introduce an algorithm for nding the clusters and a method of optimizing its parameters using machine learning techniques. The algorithm is implemented and experimentaly evaluated. For evaluation we use a manually annotated collection of Czech documents, which contains a set of sample clusters chosen and tagged by a human annotator, and a huge collection of newspaper arcticles. Experiments show that the output of our algorithm ful ls our expectation and gives clusters of topically similar texts.
|
|
|
Postmodernism in British and American comics : postmodernist overtones in the works of Alan Moore and Grant Morrison
Holub, Martin ; Ženíšek, Jakub (advisor) ; Chalupský, Petr (referee)
The aim of this thesis is the examination and analysis of postmodernist overtones in the medium of comics. It is concerned both with the postmodernist content in comics, and comics' possibilities and attributes as a postmodernist medium. The first part of the thesis elaborates on sequential art in general and the essential elements of postmodernism, such as deconstruction, metafiction, and intertextuality, within its context. The second part of the thesis is concerned with selected postmodernist works of prominent comicbook authors: Alan Moore and Grant Morrison. Key words Comics, comicbook, graphic novel, postmodernism, metafiction, intertextuality, continuum, narration, binary oppositions, deconstruction, superhero, author, creation, Watchmen, Animal Man
|
|
|
Posttranslational modifications and structural alterations of protein synthesis elongation factor Tu in Actinomyces in relation to their life cycle
Holub, Martin
Posttranslational modifications and structural alterations of protein synthesis elongation factor Tu in Actinomyces in relation to their life cycle Protein synthesis elongation factor Tu represents a multifunctional protein with potential role in signaling and regulation of cell metabolism. The complex life cycle of Streptomycetes requires monitoring of changes in their environment and signaling pathways to control it. Here we present the results of analysis of membrane phosphoproteomes from individual morphological stages of Streptomyces coelicolor with the aim to follow developmentally dependent heterogeneity and phosphorylation of intrinsic and externally added Strepomyces aureofaciens EF-Tu in membrane proteomes. We used Mycobacterium smegmatis, fast growing non-pathogenic Mycobacterium, as a non-differentiating actinomycete comparative model. Phosphorylation of intrinsic M. smegmatis and externally added Streptomyces EF-Tu was followed in membrane proteomes from exponential and stationary phase of M. smegmatis liquid culture. We have found that Streptomycetes membrane fraction contains protein kinase(s) catalyzing phosphorylation of both, its own, and an externally added EF-Tu, whereas Mycobacterium membrane fraction contains protein kinase phosphorylating only its own EF-Tu. In vitro phosphorylation...
|
guest ::
