通过顺序学习过程建立列表式生成检索模型

IF 5.4 2区 计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS
Yubao Tang, Ruqing Zhang, Jiafeng Guo, Maarten de Rijke, Wei Chen, Xueqi Cheng
{"title":"通过顺序学习过程建立列表式生成检索模型","authors":"Yubao Tang, Ruqing Zhang, Jiafeng Guo, Maarten de Rijke, Wei Chen, Xueqi Cheng","doi":"10.1145/3653712","DOIUrl":null,"url":null,"abstract":"<p>Recently, a novel generative retrieval (GR) paradigm has been proposed, where a single sequence-to-sequence model is learned to directly generate a list of relevant document identifiers (docids) given a query. Existing generative retrieval (GR) models commonly employ maximum likelihood estimation (MLE) for optimization: this involves maximizing the likelihood of a single relevant docid given an input query, with the assumption that the likelihood for each docid is independent of the other docids in the list. We refer to these models as the pointwise approach in this paper. While the pointwise approach has been shown to be effective in the context of generative retrieval (GR), it is considered sub-optimal due to its disregard for the fundamental principle that ranking involves making predictions about lists. In this paper, we address this limitation by introducing an alternative listwise approach, which empowers the generative retrieval (GR) model to optimize the relevance at the docid list level. Specifically, we view the generation of a ranked docid list as a sequence learning process: at each step we learn a subset of parameters that maximizes the corresponding generation likelihood of the <i>i</i>-th docid given the (preceding) top <i>i</i> − 1 docids. To formalize the sequence learning process, we design a positional conditional probability for generative retrieval (GR). To alleviate the potential impact of beam search on the generation quality during inference, we perform relevance calibration on the generation likelihood of model-generated docids according to relevance grades. We conduct extensive experiments on representative binary and multi-graded relevance datasets. Our empirical results demonstrate that our method outperforms state-of-the-art generative retrieval (GR) baselines in terms of retrieval performance.</p>","PeriodicalId":50936,"journal":{"name":"ACM Transactions on Information Systems","volume":null,"pages":null},"PeriodicalIF":5.4000,"publicationDate":"2024-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Listwise Generative Retrieval Models via a Sequential Learning Process\",\"authors\":\"Yubao Tang, Ruqing Zhang, Jiafeng Guo, Maarten de Rijke, Wei Chen, Xueqi Cheng\",\"doi\":\"10.1145/3653712\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Recently, a novel generative retrieval (GR) paradigm has been proposed, where a single sequence-to-sequence model is learned to directly generate a list of relevant document identifiers (docids) given a query. Existing generative retrieval (GR) models commonly employ maximum likelihood estimation (MLE) for optimization: this involves maximizing the likelihood of a single relevant docid given an input query, with the assumption that the likelihood for each docid is independent of the other docids in the list. We refer to these models as the pointwise approach in this paper. While the pointwise approach has been shown to be effective in the context of generative retrieval (GR), it is considered sub-optimal due to its disregard for the fundamental principle that ranking involves making predictions about lists. In this paper, we address this limitation by introducing an alternative listwise approach, which empowers the generative retrieval (GR) model to optimize the relevance at the docid list level. Specifically, we view the generation of a ranked docid list as a sequence learning process: at each step we learn a subset of parameters that maximizes the corresponding generation likelihood of the <i>i</i>-th docid given the (preceding) top <i>i</i> − 1 docids. To formalize the sequence learning process, we design a positional conditional probability for generative retrieval (GR). To alleviate the potential impact of beam search on the generation quality during inference, we perform relevance calibration on the generation likelihood of model-generated docids according to relevance grades. We conduct extensive experiments on representative binary and multi-graded relevance datasets. Our empirical results demonstrate that our method outperforms state-of-the-art generative retrieval (GR) baselines in terms of retrieval performance.</p>\",\"PeriodicalId\":50936,\"journal\":{\"name\":\"ACM Transactions on Information Systems\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":5.4000,\"publicationDate\":\"2024-03-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"ACM Transactions on Information Systems\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.1145/3653712\",\"RegionNum\":2,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, INFORMATION SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACM Transactions on Information Systems","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1145/3653712","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0

摘要

最近,有人提出了一种新颖的生成式检索(GR)范式,即学习一个单一的序列到序列模型来直接生成给定查询的相关文档标识符(docids)列表。现有的生成式检索(GR)模型通常采用最大似然估计法(MLE)进行优化:即在输入查询的情况下最大化单个相关文档标识符的似然,并假设每个文档标识符的似然与列表中的其他文档标识符无关。我们在本文中将这些模型称为点式方法。虽然在生成式检索(GR)中,点式方法被证明是有效的,但由于它忽视了排序涉及对列表进行预测的基本原则,因此被认为是次优方法。在本文中,我们通过引入另一种列表方法来解决这一局限性,该方法使生成式检索(GR)模型能够在 docid 列表级别优化相关性。具体来说,我们将生成一个有排序的 docid 列表视为一个序列学习过程:在每一步中,我们学习一个参数子集,该子集能最大化第 i 个 docid 在前 i - 1 个 docid 的情况下的相应生成可能性。为了使序列学习过程正规化,我们设计了生成检索(GR)的位置条件概率。为了减轻推理过程中波束搜索对生成质量的潜在影响,我们根据相关性等级对模型生成文档的生成可能性进行相关性校准。我们在具有代表性的二元和多等级相关性数据集上进行了广泛的实验。实证结果表明,我们的方法在检索性能方面优于最先进的生成式检索(GR)基线。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Listwise Generative Retrieval Models via a Sequential Learning Process

Recently, a novel generative retrieval (GR) paradigm has been proposed, where a single sequence-to-sequence model is learned to directly generate a list of relevant document identifiers (docids) given a query. Existing generative retrieval (GR) models commonly employ maximum likelihood estimation (MLE) for optimization: this involves maximizing the likelihood of a single relevant docid given an input query, with the assumption that the likelihood for each docid is independent of the other docids in the list. We refer to these models as the pointwise approach in this paper. While the pointwise approach has been shown to be effective in the context of generative retrieval (GR), it is considered sub-optimal due to its disregard for the fundamental principle that ranking involves making predictions about lists. In this paper, we address this limitation by introducing an alternative listwise approach, which empowers the generative retrieval (GR) model to optimize the relevance at the docid list level. Specifically, we view the generation of a ranked docid list as a sequence learning process: at each step we learn a subset of parameters that maximizes the corresponding generation likelihood of the i-th docid given the (preceding) top i − 1 docids. To formalize the sequence learning process, we design a positional conditional probability for generative retrieval (GR). To alleviate the potential impact of beam search on the generation quality during inference, we perform relevance calibration on the generation likelihood of model-generated docids according to relevance grades. We conduct extensive experiments on representative binary and multi-graded relevance datasets. Our empirical results demonstrate that our method outperforms state-of-the-art generative retrieval (GR) baselines in terms of retrieval performance.

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
ACM Transactions on Information Systems
ACM Transactions on Information Systems 工程技术-计算机:信息系统
CiteScore
9.40
自引率
14.30%
发文量
165
审稿时长
>12 weeks
期刊介绍: The ACM Transactions on Information Systems (TOIS) publishes papers on information retrieval (such as search engines, recommender systems) that contain: new principled information retrieval models or algorithms with sound empirical validation; observational, experimental and/or theoretical studies yielding new insights into information retrieval or information seeking; accounts of applications of existing information retrieval techniques that shed light on the strengths and weaknesses of the techniques; formalization of new information retrieval or information seeking tasks and of methods for evaluating the performance on those tasks; development of content (text, image, speech, video, etc) analysis methods to support information retrieval and information seeking; development of computational models of user information preferences and interaction behaviors; creation and analysis of evaluation methodologies for information retrieval and information seeking; or surveys of existing work that propose a significant synthesis. The information retrieval scope of ACM Transactions on Information Systems (TOIS) appeals to industry practitioners for its wealth of creative ideas, and to academic researchers for its descriptions of their colleagues'' work.
×
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:481959085
Book学术官方微信