# Two-Stage Synthesis Networks for Transfer Learning in Machine Comprehension

arXiv: https://arxiv.org/abs/1706.09789 · HTML: https://mlsanity.com/paper/1706.09789/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jun 2017.

## Built on by (most cited first, 11 of 11)

- [Contrastive Domain Adaptation for Question Answering using Limited Text Corpora](https://mlsanity.com/paper/2108.13854/) (2021)
- [Synthetic Question Value Estimation for Domain Adaptation of Question Answering](https://mlsanity.com/paper/2203.08926/) (2022)
- [OneStop QAMaker: Extract Question-Answer Pairs from Text in a One-Stop Approach](https://mlsanity.com/paper/2102.12128/) (2021)
- [Cheap and Good? Simple and Effective Data Augmentation for Low Resource Machine Reading](https://mlsanity.com/paper/2106.04134/) (2021)
- [Asking Questions Like Educational Experts: Automatically Generating Question-Answer Pairs on Real-World Examination Data](https://mlsanity.com/paper/2109.05179/) (2021)
- [BioADAPT-MRC: Adversarial Learning-based Domain Adaptation Improves Biomedical Machine Reading Comprehension Task](https://mlsanity.com/paper/2202.13174/) (2022)
- [Design and Development of Rule-based open-domain Question-Answering System on SQuAD v2.0 Dataset](https://mlsanity.com/paper/2204.09659/) (2022)
- [Graph Guided Question Answer Generation for Procedural Question-Answering](https://mlsanity.com/paper/2401.13594/) (2024)
- [Towards More Robust Natural Language Understanding](https://mlsanity.com/paper/2112.02992/) (2021)
- [QA Domain Adaptation using Hidden Space Augmentation and Self-Supervised Contrastive Adaptation](https://mlsanity.com/paper/2210.10861/) (2022)
- [DomainInv: Domain Invariant Fine Tuning and Adversarial Label Correction For QA Domain Adaptation](https://mlsanity.com/paper/2305.05589/) (2023)

## Abstract (arXiv)

We develop a technique for transfer learning in machine comprehension (MC) using a novel two-stage synthesis network (SynNet). Given a high-performing MC model in one domain, our technique aims to answer questions about documents in another domain, where we use no labeled data of question-answer pairs. Using the proposed SynNet with a pretrained model from the SQuAD dataset on the challenging NewsQA dataset, we achieve an F1 measure of 44.3% with a single model and 46.6% with an ensemble, approaching performance of in-domain models (F1 measure of 50.0%) and outperforming the out-of-domain baseline of 7.6%, without use of provided annotations.