Recently, Talmor and Berant (2018) introduced ComplexWebQuestions - a dataset focused on answering complex questions by decomposing them into a sequence of simpler questions and extracting the answer from retrieved web snippets. In their work the authors used a pre-trained reading comprehension (RC) model (Salant and Berant, 2018) to extract the answer from the web snippets. In this short note we show that training a RC model directly on the training data of ComplexWebQuestions reveals a leakage from the training set to the test set that allows to obtain unreasonably high performance. As a solution, we construct a new partitioning of ComplexWebQuestions that does not suffer from this leakage and publicly release it. We also perform an empirical evaluation on these two datasets and show that training a RC model on the training data substantially improves state-of-the-art performance.
[1]
Jonathan Berant,et al.
Building a Semantic Parser Overnight
,
2015,
ACL.
[2]
Jonathan Berant,et al.
Contextualized Word Representations for Reading Comprehension
,
2017,
NAACL.
[3]
Christopher Clark,et al.
Simple and Effective Multi-Paragraph Reading Comprehension
,
2017,
ACL.
[4]
Ming-Wei Chang,et al.
The Value of Semantic Parse Labeling for Knowledge Base Question Answering
,
2016,
ACL.
[5]
Jonathan Berant,et al.
The Web as a Knowledge-Base for Answering Complex Questions
,
2018,
NAACL.
[6]
Praveen Paritosh,et al.
Freebase: a collaboratively created graph database for structuring human knowledge
,
2008,
SIGMOD Conference.
[7]
Jian Zhang,et al.
SQuAD: 100,000+ Questions for Machine Comprehension of Text
,
2016,
EMNLP.