Original title: Odstraňování halucinací při sumarizaci grafů
Translated title: Tackling Hallucinations in Chart Summarization
Authors: Obaid ul Islam, Saad ; Dušek, Ondřej (advisor) ; Rosa, Rudolf (referee)
Document type: Master’s theses
Year: 2023
Language: eng
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
Keywords: chart-to-text generation|natural language generation|data-to-text generation|neural generative models|natural language processing|deep learning; generování popisu grafu|generování přirozeného jazyka|generování textu z dat|neuronové generativní modely|zpracování přirozeného jazyka|hluboké učení

Institution: Charles University Faculties (theses) (web)
Document availability information: Available in the Charles University Digital Repository.
Original record: http://hdl.handle.net/20.500.11956/179356

Permalink: http://www.nusl.cz/ntk/nusl-521469


The record appears in these collections:
Universities and colleges > Public universities > Charles University > Charles University Faculties (theses)
Academic theses (ETDs) > Master’s theses