|
|
Named Entity Recognition Exploiting Sub Word Information
Dobrovodský, Patrik ; Egorova, Ekaterina (oponent) ; Kesiraju, Santosh (vedoucí práce)
The aim of this thesis is the creation of a Named Entity Recognition system based on an older state-of-the-art model and studying how subword information can improve the recognition of out-of-vocabulary words. This proposed system besides English has to support two additional Indo-European languages: German and Hungarian. This work features a named entity tagger based on deep learning using pretrained and custom-trained word embeddings, sparse features, and character embeddings extracted by a Convolutional Neural Network. All these features are then processed by sequence-based (bidirectional Long Short-Term Memory) and feature-based (Conditional Random Field) approaches with the goal of achieving a F1-score similar to the work it is based on, and to compare how far present time state-of-the-art systems have evolved. The result is a system that achieves a 90.98% F1-score on the CoNLL 2003 English test dataset using pretrained word embeddings, not far behind the original work's 91.26%. For the other two languages, the model scores 89.34% on the WikiAnn German test dataset and 93.04% on the WikiAnn Hungarian test dataset with the usage of custom-trained embeddings.
|
|
|
Algorithms for named entities recognition
Winter, Luca ; Heriban, Pavel (oponent) ; Šťastný, Jiří (vedoucí práce)
The aim of this work is to find out which algorithm is the best at recognizing named entities in e-mail messages. The theoretical part explains the existing tools in this field. The practical part describes the design of two tools specifically designed to create new models capable of recognizing named entities in e-mail messages. The first tool is based on a neural network and the second tool uses a CRF graph model. The existing and newly created tools and their ability to generalize are compared on a subset of e-mail messages provided by Kiwi.com.
|
|
|
Metody strojového učení ve zpracování přirozeného jazyka
Vantuch, Marek ; Mrnuštík, Michal (oponent) ; Otrusina, Lubomír (vedoucí práce)
Práce se zabývá automatickým značkováním českého jazyka za pomocí existujících implementací, využívajících model Conditional Random Fields a algoritmy L-BFGS a SDG. Jsou popsány základní pravidla značkování a problémy, se kterými se tento obor potýká v případě zpracování českého jazyka. Čtenáři jsou vysvětleny principy použitých algoritmů a modelů, které jsou implementovány v programech CRF++ a CRFSuite. Práce se poté zaměřuje na vlastní testování úspěšnosti na českém korpusu a snaží se nalézt nejvhodnější hodnoty parametrů při využití všech rysů. Při nalezení rozumného kompromisu mezi časem a přesností se poté snaží tuto hodnotu ještě zpřesnit za pomoci analýzy přínosu jednotlivých rysů a možností jejich vynechání.
|
|
|
Image segmentation using deeplearning methods
Lukačovič, Martin ; Burget, Radim (oponent) ; Mašek, Jan (vedoucí práce)
This thesis deals with the current methods of semantic segmentation using deep learning. Other approaches of neaural networks in the area of deep learning are also discussed. It contains historical solutions of neural networks, their development, and basic principle. Convolutional neural networks are nowadays the most preferable networks in solving tasks as detection, classification, and image segmentation. The functionality was verified on a freely available environment based on conditional random fields as recurrent neural networks and compered with the deep convolutional neural networks using conditional random fields as postprocess. The latter mentioned method has become the basis for training of new models on two different datasets. There are various enviroments used to implement neural networks using deep learning, which offer diverse perform possibilities. For demonstration purposes a Python application leveraging the BVLC\,/\,Caffe framework was created. The best achieved accuracy of a trained model for clothing segmentation is 50,74\,\% and 68,52\,\% for segmentation of VOC objects. The application aims to allow interaction with image segmentation based on trained models.
|
|
|
Named Entity Recognition Exploiting Sub Word Information
Dobrovodský, Patrik ; Egorova, Ekaterina (oponent) ; Kesiraju, Santosh (vedoucí práce)
The aim of this thesis is the creation of a Named Entity Recognition system based on an older state-of-the-art model and studying how subword information can improve the recognition of out-of-vocabulary words. This proposed system besides English has to support two additional Indo-European languages: German and Hungarian. This work features a named entity tagger based on deep learning using pretrained and custom-trained word embeddings, sparse features, and character embeddings extracted by a Convolutional Neural Network. All these features are then processed by sequence-based (bidirectional Long Short-Term Memory) and feature-based (Conditional Random Field) approaches with the goal of achieving a F1-score similar to the work it is based on, and to compare how far present time state-of-the-art systems have evolved. The result is a system that achieves a 90.98% F1-score on the CoNLL 2003 English test dataset using pretrained word embeddings, not far behind the original work's 91.26%. For the other two languages, the model scores 89.34% on the WikiAnn German test dataset and 93.04% on the WikiAnn Hungarian test dataset with the usage of custom-trained embeddings.
|
|
|
Algorithms for named entities recognition
Winter, Luca ; Heriban, Pavel (oponent) ; Šťastný, Jiří (vedoucí práce)
The aim of this work is to find out which algorithm is the best at recognizing named entities in e-mail messages. The theoretical part explains the existing tools in this field. The practical part describes the design of two tools specifically designed to create new models capable of recognizing named entities in e-mail messages. The first tool is based on a neural network and the second tool uses a CRF graph model. The existing and newly created tools and their ability to generalize are compared on a subset of e-mail messages provided by Kiwi.com.
|
|
|
Image segmentation using deeplearning methods
Lukačovič, Martin ; Burget, Radim (oponent) ; Mašek, Jan (vedoucí práce)
This thesis deals with the current methods of semantic segmentation using deep learning. Other approaches of neaural networks in the area of deep learning are also discussed. It contains historical solutions of neural networks, their development, and basic principle. Convolutional neural networks are nowadays the most preferable networks in solving tasks as detection, classification, and image segmentation. The functionality was verified on a freely available environment based on conditional random fields as recurrent neural networks and compered with the deep convolutional neural networks using conditional random fields as postprocess. The latter mentioned method has become the basis for training of new models on two different datasets. There are various enviroments used to implement neural networks using deep learning, which offer diverse perform possibilities. For demonstration purposes a Python application leveraging the BVLC\,/\,Caffe framework was created. The best achieved accuracy of a trained model for clothing segmentation is 50,74\,\% and 68,52\,\% for segmentation of VOC objects. The application aims to allow interaction with image segmentation based on trained models.
|
|
|
Metody strojového učení ve zpracování přirozeného jazyka
Vantuch, Marek ; Mrnuštík, Michal (oponent) ; Otrusina, Lubomír (vedoucí práce)
Práce se zabývá automatickým značkováním českého jazyka za pomocí existujících implementací, využívajících model Conditional Random Fields a algoritmy L-BFGS a SDG. Jsou popsány základní pravidla značkování a problémy, se kterými se tento obor potýká v případě zpracování českého jazyka. Čtenáři jsou vysvětleny principy použitých algoritmů a modelů, které jsou implementovány v programech CRF++ a CRFSuite. Práce se poté zaměřuje na vlastní testování úspěšnosti na českém korpusu a snaží se nalézt nejvhodnější hodnoty parametrů při využití všech rysů. Při nalezení rozumného kompromisu mezi časem a přesností se poté snaží tuto hodnotu ještě zpřesnit za pomoci analýzy přínosu jednotlivých rysů a možností jejich vynechání.
|
host ::
RSS.