Recent advances in tabular question answering (QA) with large language models
are constrained in their coverage and only answer questions over a single
table. However, real-world queries are complex in nature, often over multiple
tables in a relational database or web page. Single table questions do not
involve common table operations such as set operations, Cartesian products
(joins), or nested queries. Furthermore, multi-table operations often result in
a tabular output, which necessitates table generation capabilities of tabular
QA models. To fill this gap, we propose a new task of answering questions over
multiple tables. Our model, MultiTabQA, not only answers questions over
multiple tables, but also generalizes to generate tabular answers. To enable
effective training, we build a pre-training dataset comprising of 132,645 SQL
queries and tabular answers. Further, we evaluate the generated tables by
introducing table-specific metrics of varying strictness assessing various
levels of granularity of the table structure. MultiTabQA outperforms
state-of-the-art single table QA models adapted to a multi-table QA setting by
finetuning on three datasets: Spider, Atis and GeoQuery.

本文提出了一种新的多表问题回答模型，称作 MultiTabQA，除了回答多表问题外，还能生成表格回答。为了实现有效的训练，我们构建了一个包括 132,645 个 SQL 查询和表格回答的预训练数据集。通过引入不同严格程度的特定于表格的评估指标，我们评估了生成的表格。经过在三个数据集（Spider、Atis 和 GeoQuery）上微调后，MultiTabQA 优于在多表 QA 环境中改编成的最先进的单表 QA 模型。

MultiTabQA：为多表问答生成表格答案

MultiTabQA: Generating Tabular Answers\\ for Multi-Table Question  Answering

Tabular question answering (TQA) presents a challenging setting for neural
systems by requiring joint reasoning of natural language with large amounts of
semi-structured data. Unlike humans who use programmatic tools like filters to
transform data before processing, language models in TQA process tables
directly, resulting in information loss as table size increases. In this paper
we propose ToolWriter to generate query specific programs and detect when to
apply them to transform tables and align them with the TQA model's
capabilities. Focusing ToolWriter to generate row-filtering tools improves the
state-of-the-art for WikiTableQuestions and WikiSQL with the most performance
gained on long tables. By investigating headroom, our work highlights the
broader potential for programmatic tools combined with neural components to
manipulate large amounts of structured data.

本文提出了 ToolWriter 算法，针对 tabular question answering 中信息丢失问题，生成查询特定的程序并检测何时将它们应用于转换表格以与 TQA 模型的能力对齐。使用 ToolWriter 生成的行过滤器工具，提高了 WikiTableQuestions 和 WikiSQL 数据集的性能。同时揭示了结构化数据中潜在的程序化工具与神经元件相结合的潜力。