Chinese word semantic relation classification based on multiple knowledge resources

机译：基于多种知识资源的汉字语义关系分类

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

Chinese word semantic relation classification is an important and challenging task in the field of natural language processing. This paper describes our method to classify Chinese word semantic relation based on multiple knowledge resources at NLPCC Evaluation. Firstly, given pairs of Chinese words, we try to utilize different knowledge resources, such as Tongyici Cilin and HowNet, to classify them into four kinds of semantic relations, which are synonym, antonym, hyponym and meronym. Secondly, for those uncovered pairs of Chinese words, we translate them into English, then classify them with the help of English knowledge resources, such as WordNet and BabelNet. Experiments on the evaluation dataset at NLPCC 2017 demonstrate that the method can achieve the macro-averaged F1-Score of 0.634 and precision of 0.875. Among all of the participants, the method get the best precision, which shows its superiority over other methods on precision.

机译：中文单词语义关系分类是自然语言处理领域一项重要而具有挑战性的任务。本文介绍了在NLPCC评估中基于多种知识资源的汉语单词语义关系分类方法。首先，给定成对的汉字，我们尝试利用不同的知识资源，如通易茨·茨林和知网，将它们分为四种语义关系，即同义词，反义词，下位词和副词。其次，对于那些未发现的中文单词，我们将它们翻译成英语，然后借助英语知识资源（如WordNet和BabelNet）对它们进行分类。在NLPCC 2017评估数据集上进行的实验表明，该方法可以实现0.634的宏平均F1-分数和0.875的精度。在所有参与者中，该方法获得了最佳精度，这表明它在精度上优于其他方法。

著录项

来源
《2017 International Conference on Security, Pattern Analysis, and Cybernetics》|2017年|372-376|共5页
会议地点 Shenzhen(CN)
作者
Fanqing Meng; Yuteng Zhang; Wenpeng Lu; Weiyu Zhang; Jinyong Cheng;
展开▼
作者单位

College of Information, Qilu University of Technology(Shandong Academy of Sciences), Jinan, China;

College of Information, Qilu University of Technology(Shandong Academy of Sciences), Jinan, China;

College of Information, Qilu University of Technology(Shandong Academy of Sciences), Jinan, China;

College of Information, Qilu University of Technology(Shandong Academy of Sciences), Jinan, China;

College of Information, Qilu University of Technology(Shandong Academy of Sciences), Jinan, China;

展开▼
会议组织
原文格式 PDF
正文语种 eng
中图分类
关键词
Semantics; Task analysis; Security; Pattern analysis; Cybernetics; Dictionaries; Natural language processing;

机译：语义;任务分析;安全性;模式分析;网络论;词典;自然语言处理;;

相似文献

外文文献
中文文献
专利

1. Using multiple Web resources and inference rules to classify Chinese word semantic relation [J] . ShutianMa, YingyiZhang, ChengzhiZhang Interlending & document supply . 2018,第2期

机译：使用多种Web资源和推理规则对汉字语义关系进行分类
2. Evaluating semantic relations in neural word embeddings with biomedical and general domain knowledge bases [J] . Zhiwei Chen, Zhe He, Xiuwen Liu, BMC Medical Informatics and Decision Making . 2018,第2期

机译：利用生物医学和通用领域知识库评估神经词嵌入中的语义关系
3. Sar-graphs: A language resource connecting linguistic knowledge with semantic relations from knowledge graphs [J] . Krause Sebastian, Hennig Leonhard, Moro Andrea, Journal of web semantics: . 2016,第MARa期

机译：Sar-graphs：一种语言资源，它将语言知识与知识图中的语义关系联系起来
4. Chinese word semantic relation classification based on multiple knowledge resources [C] . Fanqing Meng, Yuteng Zhang, Wenpeng Lu, International Conference on Security, Pattern Analysis, and Cybernetics . 2017

机译：基于多知识资源的中文语义关系分类
5. The development of Chinese word reading: Relations of sub-character processing, phonological awareness, morphological awareness, and orthographic knowledge to Chinese-English biscriptal reading. [D] . Tong, Xiuli. 2008

机译：汉语单词阅读的发展：汉字双字阅读中的子字符处理，语音意识，形态意识和拼字知识的关系。
6. Evaluating semantic relations in neural word embeddings with biomedical and general domain knowledge bases [O] . Zhiwei Chen, Zhe He, Xiuwen Liu, 2018

机译：利用生物医学和通用领域知识库评估神经词嵌入中的语义关系
7. Figure 1: (A) Example of a text-based forma mentis network. A TFMN can be represented either as an edge-coloured graph or as a multiplex network. Positive (negative) words are highlighted in cyan (red). Neutral words are in black. Syntactic links between positive (negative) words are highlighted in cyan (red) too. Syntactic links between positive and negative concepts are in purple. All semantic links of meaning overlap are highlighted in green. (B) Infographics about how a TFMN is assembled. Individuals organise their knowledge and emotional perception of the real world in their mental lexicon (comic clouds). [O] . -1

机译：图1：（a）基于文本的Forma Mentis网络示例。 TFMN可以用作边缘彩色图形或作为多路复用网络表示。在青色（红色）突出显示正（负）单词。中立词是黑色的。在青色（红色）突出显示正（否定）单词之间的句法链接。正面和消极概念之间的句法链接在紫色。含义重叠的所有语义链接都以绿色突出显示。（b）关于TFMN如何组装的信息图表。个人在他们的精神词典（漫画云）中对现实世界组织了他们的知识和情感感知。

Chinese word semantic relation classification based on multiple knowledge resources

摘要

著录项

相似文献

相关主题

期刊订阅