arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2205.13339cs.CL
收藏

基于对比学习的目标感知抽象相关工作生成

Target-aware Abstractive Related Work Generation with Contrastive Learning

Ant Group(蚂蚁集团);Peking University(北京大学);Renmin University of China(中国人民大学);University of Notre Dame(圣母大学)

Xiuying Chen, Hind Alamro, Mingzhe Li, Shen Gao, Rui Yan, Xin Gao, Xiangliang Zhang

摘要:

相关工作部分是科学论文的重要组成部分,它突出了参考论文背景下目标论文的贡献。作者可以节省他们的时间和精力,使用自动生成的相关工作部分作为草稿来完成最终的相关工作。现有的相关作品章节生成方法大多依赖于抽取现成的句子,对目标作品和参考文献进行对比讨论。然而,这样的句子需要事先写好,在实践中很难获得。因此,在本文中,我们提出了一个抽象的目标感知相关的工作生成器(TAG),它可以生成相关的工作部分组成的新的句子。具体地说,我们首先提出了一个目标感知的图编码器,它模型之间的参考文件和目标文件与目标为中心的注意力机制的关系。在解码过程中,我们提出了一个分层的解码器,参加到图中的关键词作为语义指标的不同级别的节点。最后,为了生成信息量更大的相关作品,提出了多层次对比优化目标,目标是最大化生成的相关作品与参考作品之间的互信息,最小化生成的相关作品与非参考作品之间的互信息.在两个公共学者数据集上进行的广泛实验表明,该模型在自动和定制的人类评估方面比几个强基线有了实质性的改进。

英文摘要:

The related work section is an important component of a scientific paper, which highlights the contribution of the target paper in the context of the reference papers. Authors can save their time and effort by using the automatically generated related work section as a draft to complete the final related work. Most of the existing related work section generation methods rely on extracting off-the-shelf sentences to make a comparative discussion about the target work and the reference papers. However, such sentences need to be written in advance and are hard to obtain in practice. Hence, in this paper, we propose an abstractive target-aware related work generator (TAG), which can generate related work sections consisting of new sentences. Concretely, we first propose a target-aware graph encoder, which models the relationships between reference papers and the target paper with target-centered attention mechanisms. In the decoding process, we propose a hierarchical decoder that attends to the nodes of different levels in the graph with keyphrases as semantic indicators. Finally, to generate a more informative related work, we propose multi-level contrastive optimization objectives, which aim to maximize the mutual information between the generated related work with the references and minimize that with non-references. Extensive experiments on two public scholar datasets show that the proposed model brings substantial improvements over several strong baselines in terms of automatic and tailored human evaluations.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑