当前位置:
X-MOL 学术
›
Comput. Intell. Neurosci.
›
论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Continuous Similarity Learning with Shared Neural Semantic Representation for Joint Event Detection and Evolution
Computational Intelligence and Neuroscience ( IF 3.120 ) Pub Date : 2020-12-14 , DOI: 10.1155/2020/8859407 Pengpeng Zhou 1 , Yao Luo 1 , Nianwen Ning 1 , Zhen Cao 2 , Bingjing Jia 1 , Bin Wu 1
Computational Intelligence and Neuroscience ( IF 3.120 ) Pub Date : 2020-12-14 , DOI: 10.1155/2020/8859407 Pengpeng Zhou 1 , Yao Luo 1 , Nianwen Ning 1 , Zhen Cao 2 , Bingjing Jia 1 , Bin Wu 1
Affiliation
In the era of the rapid development of today’s Internet, people often feel overwhelmed by vast official news streams or unofficial self-media tweets. To help people obtain the news topics they care about, there is a growing need for systems that can extract important events from this amount of data and construct the evolution procedure of events logically into a story. Most existing methods treat event detection and evolution as two independent subtasks under an integrated pipeline setting. However, the interdependence between these two subtasks is often ignored, which leads to a biased propagation. Besides, due to the limitations of news documents’ semantic representation, the performance of event detection and evolution is still limited. To tackle these problems, we propose a Joint Event Detection and Evolution (JEDE) model, to detect events and discover the event evolution relationships from news streams in this paper. Specifically, the proposed JEDE model is built upon the Siamese network, which first introduces the bidirectional GRU attention network to learn the vector-based semantic representation for news documents shared across two subtask networks. Then, two continuous similarity metrics are learned using stacked neural networks to judge whether two news documents are related to the same event or two events are related to the same story. Furthermore, due to the limited available dataset with ground truths, we make efforts to construct a new dataset, named EDENS, which contains valid labels of events and stories. The experimental results on this newly created dataset demonstrate that, thanks to the shared representation and joint training, the proposed model consistently achieves significant improvements over the baseline methods.
中文翻译:
具有共享神经语义表示的连续相似性学习用于联合事件检测和演化
在当今互联网快速发展的时代,人们常常被庞大的官方新闻流或非正式的自我媒体推文所淹没。为了帮助人们获得他们所关注的新闻主题,人们越来越需要能够从大量数据中提取重要事件并从逻辑上将事件演变为故事的系统。大多数现有方法在集成管道设置下将事件检测和演化视为两个独立的子任务。但是,这两个子任务之间的相互依赖性通常被忽略,这导致了有偏差的传播。此外,由于新闻文档语义表示的局限性,事件检测和演化的性能仍然受到限制。为了解决这些问题,我们提出了联合事件检测与演化(JEDE)模型,本文从新闻流中检测事件并发现事件演化关系。具体而言,所提出的JEDE模型建立在暹罗网络的基础上,该网络首先引入了双向GRU注意网络,以学习跨两个子任务网络共享的新闻文档的基于向量的语义表示。然后,使用堆叠神经网络来学习两个连续的相似性度量,以判断两个新闻文档是否与同一事件相关或两个事件与同一故事相关。此外,由于具有基本事实的可用数据集有限,我们努力构建一个名为EDENS的新数据集,其中包含事件和故事的有效标签。在这个新创建的数据集上的实验结果表明,由于有了共享的表示形式和联合训练,
更新日期:2020-12-14
中文翻译:
具有共享神经语义表示的连续相似性学习用于联合事件检测和演化
在当今互联网快速发展的时代,人们常常被庞大的官方新闻流或非正式的自我媒体推文所淹没。为了帮助人们获得他们所关注的新闻主题,人们越来越需要能够从大量数据中提取重要事件并从逻辑上将事件演变为故事的系统。大多数现有方法在集成管道设置下将事件检测和演化视为两个独立的子任务。但是,这两个子任务之间的相互依赖性通常被忽略,这导致了有偏差的传播。此外,由于新闻文档语义表示的局限性,事件检测和演化的性能仍然受到限制。为了解决这些问题,我们提出了联合事件检测与演化(JEDE)模型,本文从新闻流中检测事件并发现事件演化关系。具体而言,所提出的JEDE模型建立在暹罗网络的基础上,该网络首先引入了双向GRU注意网络,以学习跨两个子任务网络共享的新闻文档的基于向量的语义表示。然后,使用堆叠神经网络来学习两个连续的相似性度量,以判断两个新闻文档是否与同一事件相关或两个事件与同一故事相关。此外,由于具有基本事实的可用数据集有限,我们努力构建一个名为EDENS的新数据集,其中包含事件和故事的有效标签。在这个新创建的数据集上的实验结果表明,由于有了共享的表示形式和联合训练,