dc.contributor.advisor | Dušek, Ondřej | |
dc.creator | Obaid ul Islam, Saad | |
dc.date.accessioned | 2023-03-22T09:30:12Z | |
dc.date.available | 2023-03-22T09:30:12Z | |
dc.date.issued | 2023 | |
dc.identifier.uri | http://hdl.handle.net/20.500.11956/179356 | |
dc.description.abstract | Thesis Abstract Saad Obaid ul Islam Charles University, Saarland University Title Tackling Hallucinations in Chart Summarization Abstract Information visualizations like bar charts, line charts, and pie charts are a common way of communicating quantitative data. They are used to get important insights and make well informed decisions. Automatic Chart Summarization is the task to explain and summarize the key takeaways from the chart. Like other natural language generation (NLG) systems, chart summarization systems suffer from a phenomenon called halluci- nations. Hallucinations occur when the system generates text that is not grounded in the input. In this research work, we try to tackle the problem of hallucinations in chart summarization. Our analysis shows that a lot of additional information is present in the training data that leads to hallucinations during inference. We also found out that reducing long distance dependencies and addition of chart related information like title and legends improve the overall performance of the system. Furthermore, we propose a natural language inference (NLI) based method to clean the training data and show that our method produces faithful summaries. 1 | en_US |
dc.language | English | cs_CZ |
dc.language.iso | en_US | |
dc.publisher | Univerzita Karlova, Matematicko-fyzikální fakulta | cs_CZ |
dc.subject | chart-to-text generation|natural language generation|data-to-text generation|neural generative models|natural language processing|deep learning | en_US |
dc.subject | generování popisu grafu|generování přirozeného jazyka|generování textu z dat|neuronové generativní modely|zpracování přirozeného jazyka|hluboké učení | cs_CZ |
dc.title | Tackling Hallucinations in Chart Summarization | en_US |
dc.type | diplomová práce | cs_CZ |
dcterms.created | 2023 | |
dcterms.dateAccepted | 2023-01-31 | |
dc.description.department | Ústav formální a aplikované lingvistiky | cs_CZ |
dc.description.department | Institute of Formal and Applied Linguistics | en_US |
dc.description.faculty | Matematicko-fyzikální fakulta | cs_CZ |
dc.description.faculty | Faculty of Mathematics and Physics | en_US |
dc.identifier.repId | 247574 | |
dc.title.translated | Odstraňování halucinací při sumarizaci grafů | cs_CZ |
dc.contributor.referee | Rosa, Rudolf | |
thesis.degree.name | Mgr. | |
thesis.degree.level | navazující magisterské | cs_CZ |
thesis.degree.discipline | Computer Science - Language Technologies and Computational Linguistics | cs_CZ |
thesis.degree.discipline | Computer Science - Language Technologies and Computational Linguistics | en_US |
thesis.degree.program | Computer Science - Language Technologies and Computational Linguistics | cs_CZ |
thesis.degree.program | Computer Science - Language Technologies and Computational Linguistics | en_US |
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 | Computer Science - Language Technologies and Computational Linguistics | cs_CZ |
uk.degree-discipline.en | Computer Science - Language Technologies and Computational Linguistics | en_US |
uk.degree-program.cs | Computer Science - Language Technologies and Computational Linguistics | cs_CZ |
uk.degree-program.en | Computer Science - Language Technologies and Computational Linguistics | en_US |
thesis.grade.cs | Výborně | cs_CZ |
thesis.grade.en | Excellent | en_US |
uk.abstract.en | Thesis Abstract Saad Obaid ul Islam Charles University, Saarland University Title Tackling Hallucinations in Chart Summarization Abstract Information visualizations like bar charts, line charts, and pie charts are a common way of communicating quantitative data. They are used to get important insights and make well informed decisions. Automatic Chart Summarization is the task to explain and summarize the key takeaways from the chart. Like other natural language generation (NLG) systems, chart summarization systems suffer from a phenomenon called halluci- nations. Hallucinations occur when the system generates text that is not grounded in the input. In this research work, we try to tackle the problem of hallucinations in chart summarization. Our analysis shows that a lot of additional information is present in the training data that leads to hallucinations during inference. We also found out that reducing long distance dependencies and addition of chart related information like title and legends improve the overall performance of the system. Furthermore, we propose a natural language inference (NLI) based method to clean the training data and show that our method produces faithful summaries. 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 |
uk.thesis.defenceStatus | O | |