TSQA: Tabular Scenario Based Question Answering
This addresses the challenge of synthesizing tabular and textual data for AI applications like exam question answering, though it is incremental as it builds on existing MRC methods.
The paper tackles the problem of tabular scenario-based question answering (TSQA) by constructing a new dataset, GeoTSQA, with 1k geography questions, and introduces TTGen, a table-to-text generator that enhances MRC methods to outperform strong baselines.
Scenario-based question answering (SQA) has attracted an increasing research interest. Compared with the well-studied machine reading comprehension (MRC), SQA is a more challenging task: a scenario may contain not only a textual passage to read but also structured data like tables, i.e., tabular scenario based question answering (TSQA). AI applications of TSQA such as answering multiple-choice questions in high-school exams require synthesizing data in multiple cells and combining tables with texts and domain knowledge to infer answers. To support the study of this task, we construct GeoTSQA. This dataset contains 1k real questions contextualized by tabular scenarios in the geography domain. To solve the task, we extend state-of-the-art MRC methods with TTGen, a novel table-to-text generator. It generates sentences from variously synthesized tabular data and feeds the downstream MRC method with the most useful sentences. Its sentence ranking model fuses the information in the scenario, question, and domain knowledge. Our approach outperforms a variety of strong baseline methods on GeoTSQA.