使用解释方法改进模型

Zhuo Chen, Chengyue Jiang, Kewei Tu
{"title":"使用解释方法改进模型","authors":"Zhuo Chen, Chengyue Jiang, Kewei Tu","doi":"10.18653/v1/2023.emnlp-main.28","DOIUrl":null,"url":null,"abstract":"In the age of neural natural language processing, there are plenty of works trying to derive interpretations of neural models. Intuitively, when gold rationales exist during training, one can additionally train the model to match its interpretation with the rationales. However, this intuitive idea has not been fully explored. In this paper, we propose a framework of utilizing interpretation methods and gold rationales to enhance models. Our framework is very general in the sense that it can incorporate various interpretation methods. Previously proposed gradient-based methods can be shown as an instance of our framework. We also propose two novel instances utilizing two other types of interpretation methods, erasure/replace-based and extractor-based methods, for model enhancement. We conduct comprehensive experiments on a variety of tasks. Experimental results show that our framework is effective especially in low-resource settings in enhancing models with various interpretation methods, and our two newly-proposed methods outperform gradient-based methods in most settings. Code is available at https://github.com/Chord-Chen-30/UIMER.","PeriodicalId":505350,"journal":{"name":"Conference on Empirical Methods in Natural Language Processing","volume":"25 6","pages":"424-438"},"PeriodicalIF":0.0000,"publicationDate":"2024-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Using Interpretation Methods for Model Enhancement\",\"authors\":\"Zhuo Chen, Chengyue Jiang, Kewei Tu\",\"doi\":\"10.18653/v1/2023.emnlp-main.28\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In the age of neural natural language processing, there are plenty of works trying to derive interpretations of neural models. Intuitively, when gold rationales exist during training, one can additionally train the model to match its interpretation with the rationales. However, this intuitive idea has not been fully explored. In this paper, we propose a framework of utilizing interpretation methods and gold rationales to enhance models. Our framework is very general in the sense that it can incorporate various interpretation methods. Previously proposed gradient-based methods can be shown as an instance of our framework. We also propose two novel instances utilizing two other types of interpretation methods, erasure/replace-based and extractor-based methods, for model enhancement. We conduct comprehensive experiments on a variety of tasks. Experimental results show that our framework is effective especially in low-resource settings in enhancing models with various interpretation methods, and our two newly-proposed methods outperform gradient-based methods in most settings. Code is available at https://github.com/Chord-Chen-30/UIMER.\",\"PeriodicalId\":505350,\"journal\":{\"name\":\"Conference on Empirical Methods in Natural Language Processing\",\"volume\":\"25 6\",\"pages\":\"424-438\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-04-02\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Conference on Empirical Methods in Natural Language Processing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.18653/v1/2023.emnlp-main.28\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Conference on Empirical Methods in Natural Language Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.18653/v1/2023.emnlp-main.28","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

摘要

在神经自然语言处理时代,有大量工作试图推导出神经模型的解释。直观地说,当训练过程中存在黄金理由时,我们可以对模型进行额外训练,使其解释与理由相匹配。然而,这一直观想法尚未得到充分探索。在本文中,我们提出了一个利用解释方法和黄金原理来增强模型的框架。我们的框架具有很强的通用性,可以结合各种解释方法。之前提出的基于梯度的方法可以作为我们框架的一个实例。我们还提出了两个新的实例,利用另外两种解释方法(基于擦除/替换的方法和基于提取器的方法)来增强模型。我们对各种任务进行了全面的实验。实验结果表明,我们的框架在使用各种解释方法增强模型方面非常有效,尤其是在资源匮乏的情况下,我们新提出的两种方法在大多数情况下都优于基于梯度的方法。代码见 https://github.com/Chord-Chen-30/UIMER。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Using Interpretation Methods for Model Enhancement
In the age of neural natural language processing, there are plenty of works trying to derive interpretations of neural models. Intuitively, when gold rationales exist during training, one can additionally train the model to match its interpretation with the rationales. However, this intuitive idea has not been fully explored. In this paper, we propose a framework of utilizing interpretation methods and gold rationales to enhance models. Our framework is very general in the sense that it can incorporate various interpretation methods. Previously proposed gradient-based methods can be shown as an instance of our framework. We also propose two novel instances utilizing two other types of interpretation methods, erasure/replace-based and extractor-based methods, for model enhancement. We conduct comprehensive experiments on a variety of tasks. Experimental results show that our framework is effective especially in low-resource settings in enhancing models with various interpretation methods, and our two newly-proposed methods outperform gradient-based methods in most settings. Code is available at https://github.com/Chord-Chen-30/UIMER.
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
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信