Answering natural language questions using information from tables (TableQA) is of considerable recent interest. In many applications, tables occur not in isolation, but embedded in, or linked to unstructured text. Often, a question is best answered by matching its parts to either table cell contents or unstructured text spans, and extracting answers from either source. This leads to a new space of TextTableQA problems that was introduced by the HybridQA dataset. Existing adaptations of table representation to transformer-based reading comprehension (RC) architectures fail to tackle the diverse modalities of the two representations through a single system. Training such systems is further challenged by the need for distant supervision. To reduce cognitive burden, training instances usually include just the question and answer, the latter matching multiple table rows and text passages. This leads to a noisy multi-instance training regime involving not only rows of the table, but also spans of linked text. We respond to these challenges by proposing MITQA, a new TextTableQA system that explicitly models the different but closely-related probability spaces of table row selection and text span selection. Our experiments indicate the superiority of our approach compared to recent baselines. The proposed method is currently at the top of the HybridQA leaderboard with a held out test set, achieving 21 % absolute improvement on both EM and F1 scores over previous published results.
翻译:使用表格(表QA)中的信息回答自然语言问题,最近引起了相当大的兴趣。在许多应用中,表格并非孤立地出现,而是嵌入或链接到非结构化文本中。通常,一个问题最好通过将其部分匹配到表格单元格内容或无结构化文本跨度,并从两个来源中提取答案来回答。这导致混合QA数据集引入了文本列表QA问题的新空间。表格对基于变压器的阅读理解(RC)结构的现有调整未能通过单一系统解决两种表达方式的不同模式。培训这类系统受到远程监督需要的进一步挑战。为减轻认知负担,培训实例通常仅包括问答,后者匹配多个表格行和文本段落。这导致一个不仅包含表格行,而且包含相关文本的宽度的繁杂多内容培训制度。我们对这些挑战的反应是,我们提议采用新的文本QA系统,明确模拟不同但密切相关的表格行选择和文本横跨选择的概率空间。为了减少认知负担,培训实例通常只包括问答,后者匹配多个表格行和文本段落的跨行。这导致一种吵闹的多点培训制度。我们最新的混合式测试方法比了最近设定的21号测试结果。