Ta-G-T: Subjectivity Capture in Table to Text Generation via RDF Graphs

TL;DR

This paper introduces a novel three-stage pipeline for table-to-text generation that incorporates RDF triples to produce both objective and subjective narratives, improving interpretability and factual accuracy over existing large language models.

Contribution

A new structured pipeline leveraging RDFs for balanced objective and subjective table-to-text generation, outperforming some large language models in key metrics.

Findings

Achieves comparable performance to GPT-3.5

Outperforms Mistral-7B and Llama-2 in several metrics

Enhances factual accuracy and interpretability

Abstract

In Table-to-Text (T2T) generation, existing approaches predominantly focus on providing objective descriptions of tabular data. However, generating text that incorporates subjectivity, where subjectivity refers to interpretations beyond raw numerical data, remains underexplored. To address this, we introduce a novel pipeline that leverages intermediate representations to generate both objective and subjective text from tables. Our three-stage pipeline consists of: 1) extraction of Resource Description Framework (RDF) triples, 2) aggregation of text into coherent narratives, and 3) infusion of subjectivity to enrich the generated text. By incorporating RDFs, our approach enhances factual accuracy while maintaining interpretability. Unlike large language models (LLMs) such as GPT-3.5, Mistral-7B, and Llama-2, our pipeline employs smaller, fine-tuned T5 models while achieving comparable performance to GPT-3.5 and outperforming Mistral-7B and Llama-2 in several metrics. We evaluate our approach through quantitative and qualitative analyses, demonstrating its effectiveness in balancing factual accuracy with subjective interpretation. To the best of our knowledge, this is the first work to propose a structured pipeline for T2T generation that integrates intermediate representations to enhance both factual correctness and subjectivity.