当前位置: X-MOL 学术ETRI J. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Korean TableQA: Structured data question answering based on span prediction style with S3‐NET
ETRI Journal ( IF 1.3 ) Pub Date : 2020-07-26 , DOI: 10.4218/etrij.2019-0189
Cheoneum Park 1, 2 , Myungji Kim 3 , Soyoon Park 3 , Seungyoung Lim 3 , Jooyoul Lee 3 , Changki Lee 2
Affiliation  

The data in tables are accurate and rich in information, which facilitates the performance of information extraction and question answering (QA) tasks. TableQA, which is based on tables, solves problems by understanding the table structure and searching for answers to questions. In this paper, we introduce both novice and intermediate Korean TableQA tasks that involve deducing the answer to a question from structured tabular data and using it to build a question answering pair. To solve Korean TableQA tasks, we use S3‐NET, which has shown a good performance in machine reading comprehension (MRC), and propose a method of converting structured tabular data into a record format suitable for MRC. Our experimental results show that the proposed method outperforms a baseline in both the novice task (exact match (EM) 96.48% and F1 97.06%) and intermediate task (EM 99.30% and F1 99.55%).

中文翻译:

韩国语TableQA:基于S3-NET的跨度预测样式的结构化数据问答

表中的数据准确且信息丰富,这有助于执行信息提取和问题解答(QA)任务。基于表的TableQA通过了解表结构并搜索问题的答案来解决问题。在本文中,我们同时介绍了新手和中级韩语TableQA任务,这些任务涉及从结构化表格数据中推导问题的答案并使用它来构建问题答案对。为了解决韩文TableQA任务,我们使用S 3‐NET在机器阅读理解(MRC)中表现出良好的性能,并提出了一种将结构化表格数据转换为适合MRC的记录格式的方法。我们的实验结果表明,该方法在新手任务(精确匹配(EM)96.48%和F1 97.06%)和中级任务(EM 99.30%和F1 99.55%)方面均优于基线。
更新日期:2020-07-26
down
wechat
bug