面向被引片段识别的改进混合方法

A Modified Hybrid Method to Identify Cited Spans

【目的】“无监督排序+分类”模式的两阶段混合方法存在无监督排序可靠性较低、分类得到的被引句数量不稳定问题,并且被引片段的识别粒度仅限于单句。本研究对混合方法中的上述问题予以改进以提高其性能,同时解决不同粒度被引片段的识别问题。【方法】提出一种面向被引片段识别的改进混合方法,在第一阶段采用有监督排序从所有被引文献句中筛选出候选被引句,在第二阶段通过回归方法确定最终被引片段。此外,引入包含不同数量连续句子的n元句输入方式以及组内标准化方法以识别不同粒度的被引片段。【结果】在CL-SciSumm 2019和2020竞赛语料测试集上进行测评,本研究所提改进混合方法的句子重合度F1值为0.167;以3元句为输入,采用组内Z值标准化,其句子重合度F1值由0.083提高到0.158。【局限】未使用被引文献句的位置特征;在下游任务中的应用尚待探索。【结论】本研究所提改进混合方法在被引片段识别粒度为单句和多个连续单句时均取得良好效果。

[Objective] This paper proposes a new algorithm to identify the cited contents, aiming to address the issues facing the existing unsupervised models and extend the granularity of single sentence to several adjacent ones. [Methods] First, we established a modified hybrid method with supervised ranking to select candidates from all sentences of the cited literature. Then, we used regression technique to determine the sentences with the cited segments. Third, we used the grouped adjacent sentences of the cited literature, namely n-sent, as inputs to the modified hybrid method. Finally, we conducted the intraclass normalization to identify the cited contents. [Results] The modified hybrid method yielded sentence overlapping F1value of 0.167 on the test set of CL-Sci Summ 2019 and 2020. With 3-sent as input, the modified hybrid method improved the sentence overlapping F1value from 0.083 to 0.158 after intraclass Z-score normalization. [Limitations] The modified hybrid method did not utilize the sentence positions of the cited literature. In addition, the prospect of applying the proposed method to downstream tasks remains vague. [Conclusions] The proposed method could effectively identify cited segments, of which the granularity ranges from single sentence to multiple adjacent sentences.