Semi-Supervised QA with Generative Domain-Adaptive Nets

ACL 2017

Semi-Supervised QA with Generative Domain-Adaptive Nets

Jan 25, 2021
|
24 views
|
Details
Abstract: We study the problem of semi-supervised question answering----utilizing unlabeled text to boost the performance of question answering models. We propose a novel training framework, the Generative Domain-Adaptive Nets. In this framework, we train a generative model to generate questions based on the unlabeled text, and combine model-generated questions with human-generated questions for training question answering models. We develop novel domain adaptation algorithms, based on reinforcement learning, to alleviate the discrepancy between the model-generated data distribution and the human-generated data distribution. Experiments show that our proposed framework obtains substantial improvement from unlabeled text. Authors: Zhilin Yang, Junjie Hu, Ruslan Salakhutdinov, William W. Cohen (Carnegie Mellon University (Carnegie Mellon University)

Comments
loading...