QTSumm: Query-Focused Summarization over Tabular Data
This addresses the need for efficient data analysis from tables for users, but it is incremental as it builds on existing table-to-text generation methods.
The authors tackled the problem of generating tailored summaries from tables based on user queries by introducing QTSumm, a new benchmark with 7,111 query-summary pairs over 2,934 tables, and proposed ReFactor, which improved baselines by retrieving and reasoning over query-relevant information.
People primarily consult tables to conduct data analysis or answer specific questions. Text generation systems that can provide accurate table summaries tailored to users' information needs can facilitate more efficient access to relevant data insights. Motivated by this, we define a new query-focused table summarization task, where text generation models have to perform human-like reasoning and analysis over the given table to generate a tailored summary. We introduce a new benchmark named QTSumm for this task, which contains 7,111 human-annotated query-summary pairs over 2,934 tables covering diverse topics. We investigate a set of strong baselines on QTSumm, including text generation, table-to-text generation, and large language models. Experimental results and manual analysis reveal that the new task presents significant challenges in table-to-text generation for future research. Moreover, we propose a new approach named ReFactor, to retrieve and reason over query-relevant information from tabular data to generate several natural language facts. Experimental results demonstrate that ReFactor can bring improvements to baselines by concatenating the generated facts to the model input. Our data and code are publicly available at https://github.com/yale-nlp/QTSumm.