Facts-and-Feelings: Capturing both Objectivity and Subjectivity in Table-to-Text Generation
Abstract: Table-to-text generation, a long-standing challenge in natural language generation, has remained unexplored through the lens of subjectivity. Subjectivity here encompasses the comprehension of information derived from the table that cannot be described solely by objective data. Given the absence of pre-existing datasets, we introduce the \textbf{Ta2TS dataset} with \textbf{3849 data instances}. We perform the task of fine-tuning sequence-to-sequence models on the linearized tables and prompting on popular large language models. We analyze the results from a quantitative and qualitative perspective to ensure the capture of subjectivity and factual consistency. The analysis shows the fine-tuned LMs can perform close to the prompted LLMs. Both the models can capture the tabular data, generating sound texts with \textbf{85.15\%} BERTScore and \textbf{26.28\%} Meteor score. To the best of our knowledge, we provide the first kind of dataset on tables with multiple genres and subjectivity included and present the first comprehensive analysis and comparison of different LLM performances on this task.
Paper Type: Long
Research Area: Generation
Research Area Keywords: data-to-text generation
Contribution Types: Model analysis & interpretability, NLP engineering experiment, Data resources, Data analysis
Languages Studied: English
Submission Number: 830
Loading