National Repository of Grey Literature 11 records found  1 - 10next  jump to record: Search took 0.01 seconds. 
Classification of Relations between Named Entities in Text
Ondřej, Karel ; Doležal, Jan (referee) ; Smrž, Pavel (advisor)
This master thesis deals with the extraction of relationships between named entities in the text. In the theoretical part of the thesis, the issue of natural language representation for machine processing is discussed. Subsequently, two partial tasks of relationship extraction are defined, namely named entities recognition and classification of relationships between them, including a summary of state-of-the-art solutions. In the practical part of the thesis, system for automatic extraction of relationships between named entities from downloaded pages is designed. The classification of relationships between entities is based on the pre-trained transformers. In this thesis, four pre-trained transformers are compared, namely BERT, XLNet, RoBERTa and ALBERT.
Machine Learning for Natural Language Question Answering
Sasín, Jonáš ; Fajčík, Martin (referee) ; Smrž, Pavel (advisor)
This thesis deals with natural language question answering using Czech Wikipedia. Question answering systems are experiencing growing popularity, but most of them are developed for English. The main purpose of this work is to explore possibilities and datasets available and create such system for Czech. In the thesis I focused on two approaches. One of them uses English model ALBERT and machine translation of passages. The other one utilizes the multilingual BERT. Several variants of the system are compared in this work. Possibilities of relevant passage retrieval are also discussed. Standard evaluation is provided for every variant of the tested system. The best system version has been evaluated on the SQAD v3.0 dataset, reaching 0.44 EM and 0.55 F1 score, which is an excellent result compared to other existing systems. The main contribution of this work is the analysis of existing possibilities and setting a benchmark for further development of better systems for Czech.
Machine Learning for Natural Language Question Answering
Sasín, Jonáš ; Fajčík, Martin (referee) ; Smrž, Pavel (advisor)
This thesis deals with natural language question answering using Czech Wikipedia. Question answering systems are experiencing growing popularity, but most of them are developed for English. The main purpose of this work is to explore possibilities and datasets available and create such system for Czech. In the thesis I focused on two approaches. One of them uses English model ALBERT and machine translation of passages. The other one utilizes the multilingual BERT. Several variants of the system are compared in this work. Possibilities of relevant passage retrieval are also discussed. Standard evaluation is provided for every variant of the tested system. The best system version has been evaluated on the SQAD v3.0 dataset, reaching 0.44 EM and 0.55 F1 score, which is an excellent result compared to other existing systems. The main contribution of this work is the analysis of existing possibilities and setting a benchmark for further development of better systems for Czech.
Classification of Relations between Named Entities in Text
Ondřej, Karel ; Doležal, Jan (referee) ; Smrž, Pavel (advisor)
This master thesis deals with the extraction of relationships between named entities in the text. In the theoretical part of the thesis, the issue of natural language representation for machine processing is discussed. Subsequently, two partial tasks of relationship extraction are defined, namely named entities recognition and classification of relationships between them, including a summary of state-of-the-art solutions. In the practical part of the thesis, system for automatic extraction of relationships between named entities from downloaded pages is designed. The classification of relationships between entities is based on the pre-trained transformers. In this thesis, four pre-trained transformers are compared, namely BERT, XLNet, RoBERTa and ALBERT.
Assessment of the shopping atmospherics of selected stores
Do, Hai Minh ; Chylíková, Hana (advisor) ; Judová, Kateřina (referee)
This Bachelor thesis is dealing with an assessment and comparison of shopping atmospherics of two selected stores owned by chain stores Tesco Stores ČR a.s. and AHOLD Czech Republic a.s., this is followed with suggestion on improvements. This thesis is divided into four chapters. The chapter part is focused on theoretical definition of shopping atmospheric and its components. The second chapter characterizes each chain store. It describes their brief history and a present and pictures their labels and services. In a third chapter the thesis deals with the assessment of each stores through a terrain research and deals with comparison through pair comparison method and a survey. A fourth chapters objective is to suggest possible solution for improvements each components of shopping atmospheric and to show todays retail trends that can influence it.
Analýza marketingových strategií a spotřebitelského chování v lokalitě Nový Lískovec
Vetešníková, Jana
The bachelor thesis is focused on marketing communications of major retail markets compared to local stores. I've focused in my theoretical part on influence of distributions organizations impact on their surroundings. Also I focused on possible ways of promotions for the use of marketing tools and their impact on consumer's behaviour. In the empirical part is inspected the analysis of marketing communications of selected stores in Nový Lískovec and surrounding area. I've selected for my research Tesco, Albert and "Můj obchod".
Assessment of shopping atmosphere in selected stores of retail chains Albert and Billa
Šarlovský, Martin ; Chylíková, Hana (advisor) ; Komůrková, Lenka (referee)
The objective of the thesis is to assess shopping atmosphere of two selected stores Albert and one store Billa and to propose options for improving of any deficiencies. Personal visits and online survey are the chosen methods for the assessment. Thesis is divided into three chapters. The first chapter characterizes shopping atmosphere, shopping environment and business unit. The second chapter describes selected supermarkets Albert and Billa, their organizational structure, ownership and interior and exterior design of selected retail units. The third chapter is practical and assesses the own shopping atmosphere of the stores by using SWOT analysis, pairwise comparison and online survey. Evaluation of the results and proposed possible solutions for improvement of negative points are listed.
Instore marketing and its aplication at Ahold Czech Republic, a. s.
Ešner, Rudolf ; Postler, Milan (advisor) ; Eliáš, Martin (referee)
This thesis deals with an important part of marketing in retail trade -- instore marketing with a focus on commercial communications and especially sales promotions applied in Albert stores. The thesis characterizes the specifics of marketing in the retail and shopping behavior of Czech customers. The main part concerns the analysis of instore communication in Albert stores -- both its own communication and the possibilities of commercial communications of suppliers, who sell their products in supermarkets and hypermarkets Albert. The thesis also analyzes the system of selling communication space in Albert stores and a survey of effects and effectiveness of the most common sales promotions at point of sale and provides recommendations for their proper execution.

National Repository of Grey Literature : 11 records found   1 - 10next  jump to record:
Interested in being notified about new results for this query?
Subscribe to the RSS feed.