English

Repartitioning of the ComplexWebQuestions Dataset

Computation and Language 2018-07-26 v1 Artificial Intelligence Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.1807.09623,
  title  = {Repartitioning of the ComplexWebQuestions Dataset},
  author = {Alon Talmor and Jonathan Berant},
  journal= {arXiv preprint arXiv:1807.09623},
  year   = {2018}
}
R2 v1 2026-06-23T03:14:00.842Z