Generování krátkých souhrnů fotbalových zápasů v češtině ze strukturovaných dat
| Thesis title in Czech: | Generování krátkých souhrnů fotbalových zápasů v češtině ze strukturovaných dat |
|---|---|
| Thesis title in English: | Generating Short Summaries of Football Matches in the Czech Language from Structured Data |
| Key words: | Generování, strukturovaná data, souhrn informací, specifická doména |
| English key words: | Generating, structured data, short summaries, specific domain |
| Academic year of topic announcement: | 2016/2017 |
| Thesis type: | Bachelor's thesis |
| Thesis language: | |
| Department: | Institute of Formal and Applied Linguistics (32-UFAL) |
| Supervisor: | doc. RNDr. Vladislav Kuboň, Ph.D. |
| Author: | hidden - assigned and confirmed by the Study Dept. |
| Date of registration: | 26.06.2017 |
| Date of assignment: | 26.06.2017 |
| Confirmed by Study dept. on: | 28.06.2017 |
| Guidelines |
| In recent years the natural language generation has been a prominent field of computer science. There is an abundance of raw data waiting to be interpreted and the most intuitive and comprehensive way for the reader is the natural language. We will focus on creating a system working with a restricted domain, specifically the domain of short summaries of football matches. The main goal of the thesis is to develop a system that will construct a short summary of a football match in the Czech language given the structured data of the said match.
As a part of the main goal, a glossary of phrases and words typical for this domain will be created in a manual or semi-automatic way and used to improve the lexical choice. A possibility of using aggregation techniques and references based on ontological hierarchy to better mimic the natural style of written language will be investigated as well. For various subtasks we will use linguistic tools available in the LINDAT repository. |
| References |
| REITER, E., & DALE, R. (1997). Building applied natural language generation systems. *Natural Language Engineering,* *3*(1), 57-87.
Razímová Magda, Žabokrtský Zdeněk: Morphological Meanings in the Prague Dependency Treebank 2.0. In: Lecture Notes in Computer Science, Vol. 3658, Proceedings of the 8th International Conference, TSD 2005, Copyright © Springer, Berlin / Heidelberg, ISBN 3-540-28789-2, ISSN 0302-9743, pp.148-155, 2005 Ptáček Jan: Two Tectogrammatical Realizers Side by Side: Case of English and Czech. In: *Fourth International Workshop on Human-Computer Conversation*, Copyright © The Companions consortium, Bellagio, Italy, 2008 |