DETQUS: Decomposition-Enhanced Transformers for QUery-focused Summarization
This addresses the challenge of summarizing large tables based on user queries for applications in data analysis, though it is incremental as it builds on existing transformer and decomposition methods.
The paper tackled the problem of query-focused tabular summarization by introducing DETQUS, which uses decomposition to reduce table size and a fine-tuned model, achieving a ROUGE-L score of 0.4437 and outperforming the previous state-of-the-art at 0.422.
Query-focused tabular summarization is an emerging task in table-to-text generation that synthesizes a summary response from tabular data based on user queries. Traditional transformer-based approaches face challenges due to token limitations and the complexity of reasoning over large tables. To address these challenges, we introduce DETQUS (Decomposition-Enhanced Transformers for QUery-focused Summarization), a system designed to improve summarization accuracy by leveraging tabular decomposition alongside a fine-tuned encoder-decoder model. DETQUS employs a large language model to selectively reduce table size, retaining only query-relevant columns while preserving essential information. This strategy enables more efficient processing of large tables and enhances summary quality. Our approach, equipped with table-based QA model Omnitab, achieves a ROUGE-L score of 0.4437, outperforming the previous state-of-the-art REFACTOR model (ROUGE-L: 0.422). These results highlight DETQUS as a scalable and effective solution for query-focused tabular summarization, offering a structured alternative to more complex architectures.