# Semi-Supervised QA with Generative Domain-Adaptive Nets

Source: [Semi-Supervised QA with Generative Domain-Adaptive Nets](<https://www.sota2.com/research/paper/68fa63491e209131ce9fdb5f>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:37:15.413Z

Authors: Zhilin Yang, Junjie Hu, Ruslan Salakhutdinov, William W. Cohen

Published: 2017-02-07T21:23:01.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1702.02206>)

[PDF](<https://arxiv.org/pdf/1702.02206.pdf>)