PubMed摘要的概念关系质量检验

Proceedings of the 2021 5th International Conference on Natural Language Processing and Information Retrieval Pub Date : 2021-12-17 DOI:10.1145/3508230.3508243

Rajeswaran Viswanathan, S. Priya

{"title":"PubMed摘要的概念关系质量检验","authors":"Rajeswaran Viswanathan, S. Priya","doi":"10.1145/3508230.3508243","DOIUrl":null,"url":null,"abstract":"Conceptnet is a crowd sourced knowledge graph used to find relationship between words and concepts. PubMed is the largest source of documents for the bio-medical domain. From the PubMed abstracts stop words are removed and remaining words are used as seed words. For these seed words “Nearest neighbor” words are identified as candidate words using 3 popular Word Vectors (WV) - Word2Vec, Glove and FastText. Similarity is calculated for these words for each strata of relationship. Bootstrap estimator in Random Effects Model (REM) is used to study this relationship using the similarity scores. Analysis shows that there is heterogeneity among the relationships independent of the WV used as base.","PeriodicalId":252146,"journal":{"name":"Proceedings of the 2021 5th International Conference on Natural Language Processing and Information Retrieval","volume":"29 5 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Examination of the quality of Conceptnet relations for PubMed abstracts\",\"authors\":\"Rajeswaran Viswanathan, S. Priya\",\"doi\":\"10.1145/3508230.3508243\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Conceptnet is a crowd sourced knowledge graph used to find relationship between words and concepts. PubMed is the largest source of documents for the bio-medical domain. From the PubMed abstracts stop words are removed and remaining words are used as seed words. For these seed words “Nearest neighbor” words are identified as candidate words using 3 popular Word Vectors (WV) - Word2Vec, Glove and FastText. Similarity is calculated for these words for each strata of relationship. Bootstrap estimator in Random Effects Model (REM) is used to study this relationship using the similarity scores. Analysis shows that there is heterogeneity among the relationships independent of the WV used as base.\",\"PeriodicalId\":252146,\"journal\":{\"name\":\"Proceedings of the 2021 5th International Conference on Natural Language Processing and Information Retrieval\",\"volume\":\"29 5 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-12-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 2021 5th International Conference on Natural Language Processing and Information Retrieval\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3508230.3508243\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 2021 5th International Conference on Natural Language Processing and Information Retrieval","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3508230.3508243","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

摘要

Conceptnet是一个众包知识图谱，用于查找单词和概念之间的关系。PubMed是生物医学领域最大的文献来源。从PubMed摘要中删除停止词，剩余词用作种子词。对于这些种子词，“最近邻”词被识别为候选词，使用3种流行的词向量(WV) - Word2Vec, Glove和FastText。对于每一层关系，计算这些单词的相似度。随机效应模型(REM)中的自举估计器利用相似性分数来研究这种关系。分析表明，与WV无关的关系存在异质性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Examination of the quality of Conceptnet relations for PubMed abstracts

Conceptnet is a crowd sourced knowledge graph used to find relationship between words and concepts. PubMed is the largest source of documents for the bio-medical domain. From the PubMed abstracts stop words are removed and remaining words are used as seed words. For these seed words “Nearest neighbor” words are identified as candidate words using 3 popular Word Vectors (WV) - Word2Vec, Glove and FastText. Similarity is calculated for these words for each strata of relationship. Bootstrap estimator in Random Effects Model (REM) is used to study this relationship using the similarity scores. Analysis shows that there is heterogeneity among the relationships independent of the WV used as base.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Proceedings of the 2021 5th International Conference on Natural Language Processing and Information Retrieval

自引率

0.00%

发文量