改进引文文本生成：克服篇幅控制的局限性

arXiv - CS - Digital Libraries Pub Date : 2024-07-20 DOI:arxiv-2407.14997

Biswadip Mandal, Xiangci Li, Jessica Ouyang

{"title":"改进引文文本生成：克服篇幅控制的局限性","authors":"Biswadip Mandal, Xiangci Li, Jessica Ouyang","doi":"arxiv-2407.14997","DOIUrl":null,"url":null,"abstract":"A key challenge in citation text generation is that the length of generated\ntext often differs from the length of the target, lowering the quality of the\ngeneration. While prior works have investigated length-controlled generation,\ntheir effectiveness depends on knowing the appropriate generation length. In\nthis work, we present an in-depth study of the limitations of predicting\nscientific citation text length and explore the use of heuristic estimates of\ndesired length.","PeriodicalId":501285,"journal":{"name":"arXiv - CS - Digital Libraries","volume":"27 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Improving Citation Text Generation: Overcoming Limitations in Length Control\",\"authors\":\"Biswadip Mandal, Xiangci Li, Jessica Ouyang\",\"doi\":\"arxiv-2407.14997\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A key challenge in citation text generation is that the length of generated\\ntext often differs from the length of the target, lowering the quality of the\\ngeneration. While prior works have investigated length-controlled generation,\\ntheir effectiveness depends on knowing the appropriate generation length. In\\nthis work, we present an in-depth study of the limitations of predicting\\nscientific citation text length and explore the use of heuristic estimates of\\ndesired length.\",\"PeriodicalId\":501285,\"journal\":{\"name\":\"arXiv - CS - Digital Libraries\",\"volume\":\"27 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-07-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Digital Libraries\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2407.14997\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Digital Libraries","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2407.14997","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

引文文本生成的一个主要挑战是，生成文本的长度往往与目标文本的长度不同，从而降低了生成质量。虽然之前的工作已经研究了长度控制生成，但其有效性取决于是否知道合适的生成长度。在这项工作中，我们深入研究了预测科学引文文本长度的局限性，并探索了使用启发式估计期望长度的方法。

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

Improving Citation Text Generation: Overcoming Limitations in Length Control

A key challenge in citation text generation is that the length of generated text often differs from the length of the target, lowering the quality of the generation. While prior works have investigated length-controlled generation, their effectiveness depends on knowing the appropriate generation length. In this work, we present an in-depth study of the limitations of predicting scientific citation text length and explore the use of heuristic estimates of desired length.

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

arXiv - CS - Digital Libraries

自引率

0.00%

发文量