arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1805.04033cs.CL
收藏

基于语义一致性的中文社交媒体摘要输出分布规则化

Regularizing Output Distribution of Abstractive Chinese Social Media Text Summarization for Improved Semantic Consistency

Peking University(北京大学);Northwestern Polytechnical University(西北工业大学)

Bingzhen Wei, Xuancheng Ren, Xu Sun, Yi Zhang, Xiaoyan Cai, Qi Su

摘要:

摘要文本摘要是一个非常困难的问题,序列到序列模型已经成功地提高了任务的性能。然而,生成的摘要往往在语义上与源内容不一致。在这种情况下,当生成摘要时,模型选择与源内容语义无关的单词作为最可能的输出。这个问题可以归因于抽象地构造的训练数据,其中摘要可以与源内容无关,因此包含语义上不相关的单词和虚假的单词对应。在本文中,我们提出了一种正则化方法的序列到序列模型,并利用模型已经学会了正则化的学习目标,以减轻问题的影响。此外,针对现有自动评估方法无法正确评估与源内容的语义一致性的问题,我们提出了一种实用的人工评估方法。实验结果表明,该方法的有效性,它优于几乎所有现有的模型。特别是在人工评价方面,该方法将语义一致性提高了4%.

英文摘要:

Abstractive text summarization is a highly difficult problem, and the sequence-to-sequence model has shown success in improving the performance on the task. However, the generated summaries are often inconsistent with the source content in semantics. In such cases, when generating summaries, the model selects semantically unrelated words with respect to the source content as the most probable output. The problem can be attributed to heuristically constructed training data, where summaries can be unrelated to the source content, thus containing semantically unrelated words and spurious word correspondence. In this paper, we propose a regularization approach for the sequence-to-sequence model and make use of what the model has learned to regularize the learning objective to alleviate the effect of the problem. In addition, we propose a practical human evaluation method to address the problem that the existing automatic evaluation method does not evaluate the semantic consistency with the source content properly. Experimental results demonstrate the effectiveness of the proposed approach, which outperforms almost all the existing models. Especially, the proposed approach improves the semantic consistency by 4\% in terms of human evaluation.

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。

↑