|
|
Creating Dataset for Narrative Structure Recognition by Crowdsourcing
Ignác, Igor ; Dočekal, Martin (referee) ; Smrž, Pavel (advisor)
Goal of this work is creation of extensive dataset for recognition of narrative structure by crowdsourcing method. For this purpose, it was necessary to create a web interface which offers dataset of films for user annotation. The annotation of data gained from IMDb database is established on three different types of annotation. Users validate similarity of movies based on computation done by Sentence-BERT, extraction of keywords from movie plots done by RAKE and precomputed similarity between movies based on their keywords. User's gamification is based on points assignment, which are related with badges, achievements accomplishment and leader board of most successful users.
|
|
|
Keyword Suggestion in the Central Portal of Czech Libraries
Balaga, Róbert ; Otrusina, Lubomír (referee) ; Smrž, Pavel (advisor)
This thesis deals with various methods of keyphrase extraction from documents, specifically focused on documents from the Central Portal of Czech Libraries. Various methods from statistical, linguistic and graph-based methods have been implemented. Also a new method was suggested, that combines the statistical and linguistic approach. Individual methods have been tested and analyzed according to the standard evaluation metrics, with the suggested method achieving recall of 30 percent.
|
|
|
Creating Dataset for Narrative Structure Recognition by Crowdsourcing
Ignác, Igor ; Dočekal, Martin (referee) ; Smrž, Pavel (advisor)
Goal of this work is creation of extensive dataset for recognition of narrative structure by crowdsourcing method. For this purpose, it was necessary to create a web interface which offers dataset of films for user annotation. The annotation of data gained from IMDb database is established on three different types of annotation. Users validate similarity of movies based on computation done by Sentence-BERT, extraction of keywords from movie plots done by RAKE and precomputed similarity between movies based on their keywords. User's gamification is based on points assignment, which are related with badges, achievements accomplishment and leader board of most successful users.
|
|
|
Keyword Suggestion in the Central Portal of Czech Libraries
Balaga, Róbert ; Otrusina, Lubomír (referee) ; Smrž, Pavel (advisor)
This thesis deals with various methods of keyphrase extraction from documents, specifically focused on documents from the Central Portal of Czech Libraries. Various methods from statistical, linguistic and graph-based methods have been implemented. Also a new method was suggested, that combines the statistical and linguistic approach. Individual methods have been tested and analyzed according to the standard evaluation metrics, with the suggested method achieving recall of 30 percent.
|
guest ::
