@inproceedings{cho-etal-2021-contrastive,
    title = "Contrastive Multi-document Question Generation",
    author = "Cho, Woon Sang  and
      Zhang, Yizhe  and
      Rao, Sudha  and
      Celikyilmaz, Asli  and
      Xiong, Chenyan  and
      Gao, Jianfeng  and
      Wang, Mengdi  and
      Dolan, Bill",
    editor = "Merlo, Paola  and
      Tiedemann, Jorg  and
      Tsarfaty, Reut",
    booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume",
    month = apr,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.eacl-main.2",
    doi = "10.18653/v1/2021.eacl-main.2",
    pages = "12--30",
    abstract = "Multi-document question generation focuses on generating a question that covers the common aspect of multiple documents. Such a model is useful in generating clarifying options. However, a naive model trained only using the targeted ({`}positive{'}) document set may generate too generic questions that cover a larger scope than delineated by the document set. To address this challenge, we introduce the contrastive learning strategy where given {`}positive{'} and {`}negative{'} sets of documents, we generate a question that is closely related to the {`}positive{'} set but is far away from the {`}negative{'} set. This setting allows generated questions to be more specific and related to the target document set. To generate such specific questions, we propose Multi-Source Coordinated Question Generator (MSCQG), a novel framework that includes a supervised learning (SL) stage and a reinforcement learning (RL) stage. In the SL stage, a single-document question generator is trained. In the RL stage, a coordinator model is trained to find optimal attention weights to align multiple single-document generators, by optimizing a reward designed to promote specificity of generated questions. We also develop an effective auxiliary objective, named Set-induced Contrastive Regularization (SCR) that improves the coordinator{'}s contrastive learning during the RL stage. We show that our model significantly outperforms several strong baselines, as measured by automatic metrics and human evaluation. The source repository is publicly available at {`}www.github.com/woonsangcho/contrast{\_}qgen{'}.",
}