Exploring Question-Specific Rewards for Generating Deep Questions
COLING, pp. 2534-2546, 2020.
Recent question generation (QG) approaches often utilize the sequence-to-sequence framework (Seq2Seq) to optimize the log-likelihood of ground-truth questions using teacher forcing. However, this training objective is inconsistent with actual question quality, which is often reflected by certain global properties such as whether the que...More
Full Text (Upload PDF)
PPT (Upload PPT)