ID 原文 译文
56788 本文的研究成果有效解决了融合时空间维度的地理知识结构化表达和形式表示问题,为地理知识获取、融合、推理与应用奠定了基础. In conclusion, our results can effectively solve the basic problemsof GeoKG construction, which are crucial for the acquisition, fusion, reasoning, and application of geographicknowledge.
56789 同时,在地质、环境、气象等地学领域具有一定通用性,对地学知识服务的推进具有重要参考价值. Furthermore, it can be extended in geoscience fields such as geology, environmental science, andmeteorology, and has the prospects for the promotion of geoscience knowledge services.
56790 随着网络信息的剧增,信息流服务备受用户关注. Along with the explosion of web information, information flow service has attracted the attentionof users.
56791 在信息流服务中,如何衡量文本之间的相关度进而从多来源的信息渠道中过滤掉冗余信息提升推荐满意度成为至关重要的环节. In this kind of service, how to measure the correlation between texts and further filter the redundantinformation collected from multiple sources becomes the key solution to meet the user’s desire.
56792 当前主流的文本相关度计算方法均是将文本表示为向量,进而通过衡量向量之间的相似度来度量文本间的相关度. Recently, thepopular text correlation calculation methods mostly represent text as vector and then measure text similarityas text correlation.
56793 然而,信息流中的文本多为新闻文本,这些文本的核心是其描述的事件,基于此需要从事件的角度挖掘文本的核心特征进而利用其计算文本间的相关度. However, in information flow service, most of the texts are news, and the core element ina news is the event it stated. Therefore, we need a way to extract the core features that are related to theevent stated by text, so we can accurately calculate text correlation via these extracted features.
56794 当前针对事件的研究大多数着眼于句子级别. Unfortunately,recent event-related researches focus on the sentence-level.
56795 事实上,在计算文本相关度时,需要从篇章级别把握文章的内容. To calculate text correlation, we need to grasp thecontent of the text from the passage-level, which indicates that passage-level event analysis has more impact.
56796 故此,篇章级的事件分析更有影响力. Tothis end, we propose a passage-level event representation method based on sentence-level event extraction.
56797 为此,本文在句子级事件抽取的基础上,提出了一种篇章级的事件表示方法,其利用句子级事件的抽取结果构建篇章事件连通图,并选取图中重要的节点作为篇章级事件的代表,之后利用篇章级的事件表示结果来度量文本之间的相关度. Itconstructs a passage-level event connection graph based on the extracting results obtained from sentences. Afterthat, it selects the important nodes in the graph as the representations of the passage-level events. Based onthe passage-level representations, we can acquire text correlation.