基于web的科学论文摘要预训练变压器模型(WPT-SPS)

2023 International Conference on Artificial Intelligence and Smart Communication (AISC) Pub Date : 2023-01-27 DOI:10.1109/AISC56616.2023.10085409

K. Girthana, S. Swamynathan, A. R. Nirupama, S. Sri Akshya, S. Adhithyan

{"title":"基于web的科学论文摘要预训练变压器模型(WPT-SPS)","authors":"K. Girthana, S. Swamynathan, A. R. Nirupama, S. Sri Akshya, S. Adhithyan","doi":"10.1109/AISC56616.2023.10085409","DOIUrl":null,"url":null,"abstract":"The rapid growth of scientific publications becomes challenging for researchers to swiftly learn about breakthroughs in their domains. This challenge is addressed by scientific summarization, which provides summaries of the important contributions of scientific papers. This paper proposes a transfer learning technique for scientific paper summarization to generated abstractive summaries of scientific papers in a particular domain. The proposed model attained improvement of around 12% and 20% than the state-of-the art models such as BART and Longformers.","PeriodicalId":408520,"journal":{"name":"2023 International Conference on Artificial Intelligence and Smart Communication (AISC)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Web-based Pretrained Transformer Model for Scientific Paper Summarization (WPT-SPS)\",\"authors\":\"K. Girthana, S. Swamynathan, A. R. Nirupama, S. Sri Akshya, S. Adhithyan\",\"doi\":\"10.1109/AISC56616.2023.10085409\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The rapid growth of scientific publications becomes challenging for researchers to swiftly learn about breakthroughs in their domains. This challenge is addressed by scientific summarization, which provides summaries of the important contributions of scientific papers. This paper proposes a transfer learning technique for scientific paper summarization to generated abstractive summaries of scientific papers in a particular domain. The proposed model attained improvement of around 12% and 20% than the state-of-the art models such as BART and Longformers.\",\"PeriodicalId\":408520,\"journal\":{\"name\":\"2023 International Conference on Artificial Intelligence and Smart Communication (AISC)\",\"volume\":\"67 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-01-27\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2023 International Conference on Artificial Intelligence and Smart Communication (AISC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/AISC56616.2023.10085409\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 International Conference on Artificial Intelligence and Smart Communication (AISC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/AISC56616.2023.10085409","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

科学出版物的快速增长对研究人员来说是一个挑战，他们要迅速了解自己领域的突破。这一挑战是通过科学摘要来解决的，它提供了科学论文重要贡献的摘要。提出了一种科学论文摘要的迁移学习技术，用于生成特定领域的科学论文摘要。拟议的模型比BART和longformer等最先进的模型分别改善了约12%和20%。

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

Web-based Pretrained Transformer Model for Scientific Paper Summarization (WPT-SPS)

The rapid growth of scientific publications becomes challenging for researchers to swiftly learn about breakthroughs in their domains. This challenge is addressed by scientific summarization, which provides summaries of the important contributions of scientific papers. This paper proposes a transfer learning technique for scientific paper summarization to generated abstractive summaries of scientific papers in a particular domain. The proposed model attained improvement of around 12% and 20% than the state-of-the art models such as BART and Longformers.

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

2023 International Conference on Artificial Intelligence and Smart Communication (AISC)

自引率

0.00%

发文量