|
|
Computer as an Intelligent Partner in the Word-Association Game Codenames
Chovancová, Kateřina ; Dočekal, Martin (referee) ; Smrž, Pavel (advisor)
This thesis extends a system for determining semantic similarity between words and creating word associations. For this purpose, the work uses the fastText predictive model in combination with the DETECT method, and model based on Pointwise Mutual Information calculation. DETECT method uses Dict2vec model, which is trained on dictionary definitions of terms. The resulting system is capable of replacing a player in the word association game Codenames, both as a member of an operative and as a spy. Furthermore, a tool for creating semantic control and knowledge tests was developed within the thesis, which uses a dictionary of Czech synonyms and is used to calculate the TDS value and determine the frequency of occurrence of words. The last part of the thesis is devoted to the analysis of data from the STST II. study, in which players’ inter-thought connections while playing a communication game were investigated.
|
|
|
Word Sense Clustering
Haljuk, Petr ; Otrusina, Lubomír (referee) ; Smrž, Pavel (advisor)
This Bachelor's thesis deals with the semantic similarity of words . It describes the design and the implementation of a system, which searches for the most similar words and measures the semantic similarity of words . The system uses the Word2Vec model from GenSim library . It learns the relations among words from CommonCrawl corpus .
|
|
|
Word2vec Models with Added Context Information
Šůstek, Martin ; Rozman, Jaroslav (referee) ; Zbořil, František (advisor)
This thesis is concerned with the explanation of the word2vec models. Even though word2vec was introduced recently (2013), many researchers have already tried to extend, understand or at least use the model because it provides surprisingly rich semantic information. This information is encoded in N-dim vector representation and can be recall by performing some operations over the algebra. As an addition, I suggest a model modifications in order to obtain different word representation. To achieve that, I use public picture datasets. This thesis also includes parts dedicated to word2vec extension based on convolution neural network.
|
|
|
Word Sense Clustering
Hošták, Viliam Samuel ; Otrusina, Lubomír (referee) ; Smrž, Pavel (advisor)
This thesis deals with semantic similarity of words. It describes and compares existing models that are currently used for this purpose. It discusses the design and implementation of the system for corpus preprocessing, semantic modelling and retrieval of semantically related words. The system that has been created supports the use of distributional semantic models Word2vec, FastText and Glove.
|
|
| |
|
|
Word Sense Clustering
Jadrníček, Zbyněk ; Otrusina, Lubomír (referee) ; Smrž, Pavel (advisor)
This thesis is focused on the problem of semantic similarity of words in English language. At first reader is informed about theory of word sense clustering, then there are described chosen methods and tools related to the topic. In the practical part we design and implement system for determining semantic similarity using Word2Vec tool, particularly we focus on biomedical texts of MEDLINE database. At the end of the thesis we discuss reached results and give some ideas to improve the system.
|
|
| |
|
|
A Tool for Recognition and Verification of Spedition Orders
Kalivoda, Vojtěch ; Hradiš, Michal (referee) ; Herout, Adam (advisor)
The aim of this work is to design and implement a web tool that will facilitate the work of dispatchers of forwarding and transport companies through automated recognition of important information in orders. Thanks to the recognition, not all information has to be manually rewritten by dispatchers, which saves time. Order recognition is based on finding entities in a document, representing its surroundings with vectors using word2vec models and subsequent classification using convolutional neural networks. The tool can recognize 20 types of information in real time with an average success rate of 72.35~\%. As part of the work, a dataset of almost 1~700 orders was collected and 141 of them were annotated. Part of the work is a web application that serves as an interface for the tool and data collection.
|
|
|
Binární klasifikace zákaznických incidentů pomocí metod NLP
Pokorný, Jiří
This bachelor thesis focuses on building a model for binary classification of customer incidents within the SAP system. By classifying the individual sentences of incidents, the final category of the incident is predicted. The used text is in English. To compare traditional and modern approaches to text classification as well as obtain optimal results, a series of experiments is carried out using different methods of balancing the dataset, vector representation and classification. Finally, the results are analyzed and recommendation is formulated with regard to further development, including applying knowledge gained within the SAP environment.
|
|
|
A Tool for Recognition and Verification of Spedition Orders
Kalivoda, Vojtěch ; Hradiš, Michal (referee) ; Herout, Adam (advisor)
The aim of this work is to design and implement a web tool that will facilitate the work of dispatchers of forwarding and transport companies through automated recognition of important information in orders. Thanks to the recognition, not all information has to be manually rewritten by dispatchers, which saves time. Order recognition is based on finding entities in a document, representing its surroundings with vectors using word2vec models and subsequent classification using convolutional neural networks. The tool can recognize 20 types of information in real time with an average success rate of 72.35~\%. As part of the work, a dataset of almost 1~700 orders was collected and 141 of them were annotated. Part of the work is a web application that serves as an interface for the tool and data collection.
|
guest ::
