| dc.contributor.advisor | Mareček, David | |
| dc.creator | de Rijk, Micha Theo Neri | |
| dc.date.accessioned | 2020-02-25T10:55:20Z | |
| dc.date.available | 2020-02-25T10:55:20Z | |
| dc.date.issued | 2020 | |
| dc.identifier.uri | http://hdl.handle.net/20.500.11956/116657 | |
| dc.description.abstract | Micha de Rijk January 6, 2020 Word association is an important part of human language. Many techniques for capturing semantic relations between words exist, but their ability to model word associations is rarely tested. We introduce the game of Codenames with one human player as a word association task to evaluate how well a language model captures this information. We establish the baseline f-score of 0.362 and explore the performance of several collocations and word embedding models on this task. Our best model uses fastText word embeddings and achieves an f-score of 0.789 for Czech and 0.751 for English. 1 | en_US |
| dc.language | English | cs_CZ |
| dc.language.iso | en_US | |
| dc.publisher | Univerzita Karlova, Matematicko-fyzikální fakulta | cs_CZ |
| dc.subject | umělá inteligence | cs_CZ |
| dc.subject | jazyk | cs_CZ |
| dc.subject | hra | cs_CZ |
| dc.subject | slovní asociace | cs_CZ |
| dc.subject | computational word association | en_US |
| dc.subject | codenames | en_US |
| dc.subject | pointwise mutual information | en_US |
| dc.subject | word embeddings | en_US |
| dc.title | Codenames: a practical application for modelling word association | en_US |
| dc.type | diplomová práce | cs_CZ |
| dcterms.created | 2020 | |
| dcterms.dateAccepted | 2020-02-04 | |
| dc.description.department | Ústav formální a aplikované lingvistiky | cs_CZ |
| dc.description.department | Institute of Formal and Applied Linguistics | en_US |
| dc.description.faculty | Faculty of Mathematics and Physics | en_US |
| dc.description.faculty | Matematicko-fyzikální fakulta | cs_CZ |
| dc.identifier.repId | 207412 | |
| dc.title.translated | Umělá inteligence pro Krycí jména: hru založenou na slovních asociacích | cs_CZ |
| dc.contributor.referee | Popel, Martin | |
| thesis.degree.name | Mgr. | |
| thesis.degree.level | navazující magisterské | cs_CZ |
| thesis.degree.discipline | Computational Linguistics | en_US |
| thesis.degree.discipline | Matematická lingvistika | cs_CZ |
| thesis.degree.program | Computer Science | en_US |
| thesis.degree.program | Informatika | cs_CZ |
| uk.thesis.type | diplomová práce | cs_CZ |
| uk.taxonomy.organization-cs | Matematicko-fyzikální fakulta::Ústav formální a aplikované lingvistiky | cs_CZ |
| uk.taxonomy.organization-en | Faculty of Mathematics and Physics::Institute of Formal and Applied Linguistics | en_US |
| uk.faculty-name.cs | Matematicko-fyzikální fakulta | cs_CZ |
| uk.faculty-name.en | Faculty of Mathematics and Physics | en_US |
| uk.faculty-abbr.cs | MFF | cs_CZ |
| uk.degree-discipline.cs | Matematická lingvistika | cs_CZ |
| uk.degree-discipline.en | Computational Linguistics | en_US |
| uk.degree-program.cs | Informatika | cs_CZ |
| uk.degree-program.en | Computer Science | en_US |
| thesis.grade.cs | Výborně | cs_CZ |
| thesis.grade.en | Excellent | en_US |
| uk.abstract.en | Micha de Rijk January 6, 2020 Word association is an important part of human language. Many techniques for capturing semantic relations between words exist, but their ability to model word associations is rarely tested. We introduce the game of Codenames with one human player as a word association task to evaluate how well a language model captures this information. We establish the baseline f-score of 0.362 and explore the performance of several collocations and word embedding models on this task. Our best model uses fastText word embeddings and achieves an f-score of 0.789 for Czech and 0.751 for English. 1 | en_US |
| uk.file-availability | V | |
| uk.grantor | Univerzita Karlova, Matematicko-fyzikální fakulta, Ústav formální a aplikované lingvistiky | cs_CZ |
| thesis.grade.code | 1 | |
| uk.publication-place | Praha | cs_CZ |
