Due to the concise and structured nature of tables, the knowledge contained
therein may be incomplete or missing, posing a significant challenge for table
question answering (TableQA) and data analysis systems. Most existing datasets
either fail to address the issue of external knowledge in TableQA or only
utilize unstructured text as supplementary information for tables. In this
paper, we propose to use a knowledge base (KB) as the external knowledge source
for TableQA and construct a dataset KET-QA with fine-grained gold evidence
annotation. Each table in the dataset corresponds to a sub-graph of the entire
KB, and every question requires the integration of information from both the
table and the sub-graph to be answered. To extract pertinent information from
the vast knowledge sub-graph and apply it to TableQA, we design a
retriever-reasoner structured pipeline model. Experimental results demonstrate
that our model consistently achieves remarkable relative performance
improvements ranging from 1.9 to 6.5 times and absolute improvements of 11.66%
to 44.64% on EM scores across three distinct settings (fine-tuning, zero-shot,
and few-shot), in comparison with solely relying on table information in the
traditional TableQA manner. However, even the best model achieves a 60.23% EM
score, which still lags behind the human-level performance, highlighting the
challenging nature of KET-QA for the question-answering community. We also
provide a human evaluation of error cases to analyze further the aspects in
which the model can be improved. Project page: this https URL

这篇论文介绍了一种使用知识库作为表格问答的外部知识源，并构建了一个带有精细化知识注释的数据集 KET-QA。通过设计检索 - 推理结构化流水线模型，实验结果表明，该模型在三个不同场景（微调、零样本和少样本）中相对性能提升范围为 1.9 至 6.5 倍，绝对性能提升范围为 11.66% 至 44.64%。然而，即使是最好的模型也只达到了 60.23% 的 EM 得分，仍然落后于人类水平，突显了 KET-QA 对问答研究领域的挑战性。

KET-QA：用于知识增强表格问答的数据集

KET-QA: A Dataset for Knowledge Enhanced Table Question Answering

Machine reading comprehension is an essential natural language processing
task, which takes into a pair of context and query and predicts the
corresponding answer to query. In this project, we developed an end-to-end
question answering model incorporating BERT and additional linguistic features.
We conclude that the BERT base model will be improved by incorporating the
features. The EM score and F1 score are improved 2.17 and 2.14 compared with
BERT(base). Our best single model reaches EM score 76.55 and F1 score 79.97 in
the hidden test set. Our error analysis also shows that the linguistic
architecture can help model understand the context better in that it can locate
answers that BERT only model predicted "No Answer" wrongly.

我们开发了一个整合了 BERT 和其他语言特征的端到端问题回答模型，结果表明这种模型能够改善 BERT 基础模型，EM 得分和 F1 得分分别提高了 2.17 和 2.14。我们的最佳单一模型在隐藏测试集上达到了 EM 得分 76.55 和 F1 得分 79.97。我们的错误分析还表明，语言结构可以帮助模型更好地理解上下文，从而纠正 BERT 模型将答案错误预测为 “无答案” 的情况。