Profiling News Discourse Structure Using Explicit Subtopic Structures Guided Critics
Profiling News Discourse Structure Using Explicit Subtopic Structures Guided Critics
复制标题
DOI：
10.18653/v1/2021.findings-emnlp.137
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Prafulla Kumar Choubey;Ruihong Huang
中科院分区：
文献类型：
--
作者：
Prafulla Kumar Choubey;Ruihong Huang
我们提出了一个演员-批评者框架来归纳新闻文章中的次话题结构，以支持fiLing的新闻语篇。该模型使用了多个评论家，他们根据已知的副主题结构行事，而演员的目标是超越他们。内容结构构成的句子代表了潜在的副话题界限-白羊座。然后，我们引入了一个层次神经网络，它使用识别的fi子主题边界语句来建模句子、子主题和文档之间的多层交互。实验结果和在新闻语篇语料库上的分析表明，角色模型学习了有效地将文档分割为子主题，并提高了层次模型在新闻语篇处理fi任务1上的性能。以随机种子运行。此外，我们还报告了F1宏观和微观得分的标准差。统计学显著性fi检验表明，在配对t检验中，RL-IP/TT模型的宏观和微观F1分数均显著好于具有p<；0.05的等级、自我批评、文本拼贴和联合IP模型(Dietterich，1998)。同样，RL-TT和RL-IP模型的宏观F1得分明显好于具有p<；0.05的分层、文本和联合IP模型。
We present an actor-critic framework to induce subtopical structures in a news article for news discourse profiling. The model uses multiple critics that act according to known subtopic structures while the actor aims to outperform them. The content structures constitute sentences that represent latent subtopic bound-aries. Then, we introduce a hierarchical neural network that uses the identified subtopic boundary sentences to model multi-level interaction between sentences, subtopics, and the document. Experimental results and analyses on the NewsDiscourse corpus show that the actor model learns to effectively segment a document into subtopics and improves the performance of the hierarchical model on the news discourse profiling task 1 . runs with random seeds. In addition, we report standard deviation for both macro and micro F1 scores. Statistical significance tests show that both the macro and micro F1 scores for RL-IP/TT model are significantly better compared to the hierarchical, self-critic, TextTiling and joint-IP models with p < 0.05 on paired t test (Dietterich, 1998). Similarly, the macro F1 scores for RL-TT and RL-IP models are significantly better compared to the hierarchical, TextTiling and Joint-IP models with p < 0.05.