首页 > 最新文献

ACM Transactions on Information Systems (TOIS)最新文献

英文 中文
Multi-interest Diversification for End-to-end Sequential Recommendation 端到端顺序推荐的多利益多样化
Pub Date : 2021-09-07 DOI: 10.1145/3475768
Wanyu Chen, Pengjie Ren, Fei Cai, Fei Sun, Maarten de Rijke
Sequential recommenders capture dynamic aspects of users’ interests by modeling sequential behavior. Previous studies on sequential recommendations mostly aim to identify users’ main recent interests to optimize the recommendation accuracy; they often neglect the fact that users display multiple interests over extended periods of time, which could be used to improve the diversity of lists of recommended items. Existing work related to diversified recommendation typically assumes that users’ preferences are static and depend on post-processing the candidate list of recommended items. However, those conditions are not suitable when applied to sequential recommendations. We tackle sequential recommendation as a list generation process and propose a unified approach to take accuracy as well as diversity into consideration, called multi-interest, diversified, sequential recommendation. Particularly, an implicit interest mining module is first used to mine users’ multiple interests, which are reflected in users’ sequential behavior. Then an interest-aware, diversity promoting decoder is designed to produce recommendations that cover those interests. For training, we introduce an interest-aware, diversity promoting loss function that can supervise the model to learn to recommend accurate as well as diversified items. We conduct comprehensive experiments on four public datasets and the results show that our proposal outperforms state-of-the-art methods regarding diversity while producing comparable or better accuracy for sequential recommendation.
顺序推荐通过对顺序行为建模来捕获用户兴趣的动态方面。以往关于顺序推荐的研究主要是为了识别用户最近的主要兴趣,以优化推荐的准确性;他们经常忽略这样一个事实,即用户会在很长一段时间内显示多种兴趣,这可以用来改善推荐项目列表的多样性。与多样化推荐相关的现有工作通常假设用户的偏好是静态的,并且依赖于对推荐项目候选列表的后处理。但是,这些条件不适用于顺序建议。我们将顺序推荐作为一个列表生成过程来处理,并提出了一种兼顾准确性和多样性的统一方法,称为多兴趣、多样化、顺序推荐。其中,首先使用隐式兴趣挖掘模块挖掘用户的多个兴趣,这些兴趣反映在用户的顺序行为中。然后设计一个兴趣感知,多样性促进解码器,以产生涵盖这些兴趣的建议。对于训练,我们引入了一个兴趣感知、多样性促进损失函数,可以监督模型学习推荐准确和多样化的项目。我们在四个公共数据集上进行了全面的实验,结果表明,我们的建议在多样性方面优于最先进的方法,同时对顺序推荐产生相当或更好的准确性。
{"title":"Multi-interest Diversification for End-to-end Sequential Recommendation","authors":"Wanyu Chen, Pengjie Ren, Fei Cai, Fei Sun, Maarten de Rijke","doi":"10.1145/3475768","DOIUrl":"https://doi.org/10.1145/3475768","url":null,"abstract":"Sequential recommenders capture dynamic aspects of users’ interests by modeling sequential behavior. Previous studies on sequential recommendations mostly aim to identify users’ main recent interests to optimize the recommendation accuracy; they often neglect the fact that users display multiple interests over extended periods of time, which could be used to improve the diversity of lists of recommended items. Existing work related to diversified recommendation typically assumes that users’ preferences are static and depend on post-processing the candidate list of recommended items. However, those conditions are not suitable when applied to sequential recommendations. We tackle sequential recommendation as a list generation process and propose a unified approach to take accuracy as well as diversity into consideration, called multi-interest, diversified, sequential recommendation. Particularly, an implicit interest mining module is first used to mine users’ multiple interests, which are reflected in users’ sequential behavior. Then an interest-aware, diversity promoting decoder is designed to produce recommendations that cover those interests. For training, we introduce an interest-aware, diversity promoting loss function that can supervise the model to learn to recommend accurate as well as diversified items. We conduct comprehensive experiments on four public datasets and the results show that our proposal outperforms state-of-the-art methods regarding diversity while producing comparable or better accuracy for sequential recommendation.","PeriodicalId":6934,"journal":{"name":"ACM Transactions on Information Systems (TOIS)","volume":"56 1","pages":"1 - 30"},"PeriodicalIF":0.0,"publicationDate":"2021-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82758840","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 21
A Review on Question Generation from Natural Language Text 自然语言文本问题生成研究综述
Pub Date : 2021-09-07 DOI: 10.1145/3468889
Ruqing Zhang, Jiafeng Guo, Luyao Chen, Yixing Fan, Xueqi Cheng
Question generation is an important yet challenging problem in Artificial Intelligence (AI), which aims to generate natural and relevant questions from various input formats, e.g., natural language text, structure database, knowledge base, and image. In this article, we focus on question generation from natural language text, which has received tremendous interest in recent years due to the widespread applications such as data augmentation for question answering systems. During the past decades, many different question generation models have been proposed, from traditional rule-based methods to advanced neural network-based methods. Since there have been a large variety of research works proposed, we believe it is the right time to summarize the current status, learn from existing methodologies, and gain some insights for future development. In contrast to existing reviews, in this survey, we try to provide a more comprehensive taxonomy of question generation tasks from three different perspectives, i.e., the types of the input context text, the target answer, and the generated question. We take a deep look into existing models from different dimensions to analyze their underlying ideas, major design principles, and training strategies We compare these models through benchmark tasks to obtain an empirical understanding of the existing techniques. Moreover, we discuss what is missing in the current literature and what are the promising and desired future directions.
问题生成是人工智能(AI)中的一个重要而又具有挑战性的问题,它旨在从各种输入格式(如自然语言文本、结构数据库、知识库和图像)中生成自然且相关的问题。在本文中,我们主要关注自然语言文本的问题生成,近年来,由于问答系统的数据增强等广泛应用,自然语言文本的问题生成受到了极大的关注。在过去的几十年里,人们提出了许多不同的问题生成模型,从传统的基于规则的方法到先进的基于神经网络的方法。由于提出了各种各样的研究工作,我们认为现在是总结现状,学习现有方法,并为未来发展提供一些见解的合适时机。与现有的综述相比,在本次调查中,我们试图从三个不同的角度(即输入上下文文本的类型、目标答案和生成的问题)提供更全面的问题生成任务分类。我们从不同的维度深入研究现有的模型,分析它们的基本思想、主要设计原则和训练策略。我们通过基准任务对这些模型进行比较,以获得对现有技术的经验理解。此外,我们还讨论了当前文献中缺失的内容以及有希望和期望的未来方向。
{"title":"A Review on Question Generation from Natural Language Text","authors":"Ruqing Zhang, Jiafeng Guo, Luyao Chen, Yixing Fan, Xueqi Cheng","doi":"10.1145/3468889","DOIUrl":"https://doi.org/10.1145/3468889","url":null,"abstract":"Question generation is an important yet challenging problem in Artificial Intelligence (AI), which aims to generate natural and relevant questions from various input formats, e.g., natural language text, structure database, knowledge base, and image. In this article, we focus on question generation from natural language text, which has received tremendous interest in recent years due to the widespread applications such as data augmentation for question answering systems. During the past decades, many different question generation models have been proposed, from traditional rule-based methods to advanced neural network-based methods. Since there have been a large variety of research works proposed, we believe it is the right time to summarize the current status, learn from existing methodologies, and gain some insights for future development. In contrast to existing reviews, in this survey, we try to provide a more comprehensive taxonomy of question generation tasks from three different perspectives, i.e., the types of the input context text, the target answer, and the generated question. We take a deep look into existing models from different dimensions to analyze their underlying ideas, major design principles, and training strategies We compare these models through benchmark tasks to obtain an empirical understanding of the existing techniques. Moreover, we discuss what is missing in the current literature and what are the promising and desired future directions.","PeriodicalId":6934,"journal":{"name":"ACM Transactions on Information Systems (TOIS)","volume":"54 1","pages":"1 - 43"},"PeriodicalIF":0.0,"publicationDate":"2021-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86620037","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 26
Multi-Stage Conversational Passage Retrieval: An Approach to Fusing Term Importance Estimation and Neural Query Rewriting 多阶段会话段落检索:一种融合词重要性估计和神经查询重写的方法
Pub Date : 2021-08-31 DOI: 10.1145/3446426
Sheng-Chieh Lin, Jheng-Hong Yang, Rodrigo Nogueira, Ming-Feng Tsai, Chuan-Ju Wang, Jimmy J. Lin
Conversational search plays a vital role in conversational information seeking. As queries in information seeking dialogues are ambiguous for traditional ad hoc information retrieval (IR) systems due to the coreference and omission resolution problems inherent in natural language dialogue, resolving these ambiguities is crucial. In this article, we tackle conversational passage retrieval, an important component of conversational search, by addressing query ambiguities with query reformulation integrated into a multi-stage ad hoc IR system. Specifically, we propose two conversational query reformulation (CQR) methods: (1) term importance estimation and (2) neural query rewriting. For the former, we expand conversational queries using important terms extracted from the conversational context with frequency-based signals. For the latter, we reformulate conversational queries into natural, stand-alone, human-understandable queries with a pretrained sequence-to-sequence model. Detailed analyses of the two CQR methods are provided quantitatively and qualitatively, explaining their advantages, disadvantages, and distinct behaviors. Moreover, to leverage the strengths of both CQR methods, we propose combining their output with reciprocal rank fusion, yielding state-of-the-art retrieval effectiveness, 30% improvement in terms of NDCG@3 compared to the best submission of Text REtrieval Conference (TREC) Conversational Assistant Track (CAsT) 2019.
会话搜索在会话信息搜索中起着至关重要的作用。由于自然语言对话中固有的共指和遗漏解决问题,使得传统的信息检索系统在信息搜索对话中查询具有歧义性,因此解决这些歧义性至关重要。在本文中,我们通过将查询重构集成到多阶段临时IR系统中来解决查询歧义,从而解决会话通道检索(会话搜索的一个重要组成部分)。具体而言,我们提出了两种会话查询重构(CQR)方法:(1)项重要性估计和(2)神经查询重写。对于前者,我们使用基于频率的信号从会话上下文中提取的重要术语扩展会话查询。对于后者,我们使用预训练的序列到序列模型将会话查询重新表述为自然的、独立的、人类可理解的查询。对两种CQR方法进行了定量和定性的详细分析,说明了它们的优缺点和不同的行为。此外,为了利用这两种CQR方法的优势,我们建议将它们的输出与互序融合相结合,产生最先进的检索效率,与2019年文本检索会议(TREC)会话助理轨道(CAsT)的最佳提交相比,NDCG@3提高了30%。
{"title":"Multi-Stage Conversational Passage Retrieval: An Approach to Fusing Term Importance Estimation and Neural Query Rewriting","authors":"Sheng-Chieh Lin, Jheng-Hong Yang, Rodrigo Nogueira, Ming-Feng Tsai, Chuan-Ju Wang, Jimmy J. Lin","doi":"10.1145/3446426","DOIUrl":"https://doi.org/10.1145/3446426","url":null,"abstract":"Conversational search plays a vital role in conversational information seeking. As queries in information seeking dialogues are ambiguous for traditional ad hoc information retrieval (IR) systems due to the coreference and omission resolution problems inherent in natural language dialogue, resolving these ambiguities is crucial. In this article, we tackle conversational passage retrieval, an important component of conversational search, by addressing query ambiguities with query reformulation integrated into a multi-stage ad hoc IR system. Specifically, we propose two conversational query reformulation (CQR) methods: (1) term importance estimation and (2) neural query rewriting. For the former, we expand conversational queries using important terms extracted from the conversational context with frequency-based signals. For the latter, we reformulate conversational queries into natural, stand-alone, human-understandable queries with a pretrained sequence-to-sequence model. Detailed analyses of the two CQR methods are provided quantitatively and qualitatively, explaining their advantages, disadvantages, and distinct behaviors. Moreover, to leverage the strengths of both CQR methods, we propose combining their output with reciprocal rank fusion, yielding state-of-the-art retrieval effectiveness, 30% improvement in terms of NDCG@3 compared to the best submission of Text REtrieval Conference (TREC) Conversational Assistant Track (CAsT) 2019.","PeriodicalId":6934,"journal":{"name":"ACM Transactions on Information Systems (TOIS)","volume":"3 1","pages":"1 - 29"},"PeriodicalIF":0.0,"publicationDate":"2021-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87778704","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 41
Conversational Search and Recommendation: Introduction to the Special Issue 会话搜索和推荐:特刊导论
Pub Date : 2021-08-31 DOI: 10.1145/3465272
C. Hauff, Julia Kiseleva, M. Sanderson, Hamed Zamani, Yongfeng Zhang
While conversational search and recommendation has roots in early Information Retrieval (IR) research, the recent advances in automatic voice recognition and conversational agents have created increasing interest in this area. This topic was recognized as an emerging research area in the Third Strategic Workshop on Information Retrieval in Lorne (SWIRL 2018) [Culpepper et al. 2018]. Conversational search and recommendation systems consist of multiple components, from user modeling to conversational understanding to query modeling to result presentation. In recent years, the IR and related communities have witnessed a number of major contributions to the field of conversational search and recommendation. They include but are not limited to conversational search conceptualization (e.g., Azzopardi et al. [2018], Deldjoo et al. [2021], and Radlinski and Craswell [2017]), effective conversational query re-writing (e.g., Yu et al. [2020]), generating and selecting clarifying questions (e.g., Zamani et al. [2020a, c]), conversational preference elicitation (e.g., Radlinski et al. [2019] and Zhang et al. [2018]), and understanding user interactions with spoken conversational systems (e.g., Trippas et al. [2018, 2020]). The growing body of work in this area has been supplemented by an increasing number of recent seminars (e.g., Anand et al. [2020]), workshops (e.g., Arguello et al. [2018], Burtsev et al. [2017], Chuklin et al. [2018], and
虽然会话搜索和推荐起源于早期的信息检索(IR)研究,但最近在自动语音识别和会话代理方面的进展使人们对这一领域的兴趣越来越大。该主题在洛恩第三届信息检索战略研讨会(SWIRL 2018)中被认为是一个新兴的研究领域[Culpepper et al. 2018]。会话搜索和推荐系统由多个组件组成,从用户建模到会话理解、查询建模到结果表示。近年来,IR和相关社区见证了会话搜索和推荐领域的许多重大贡献。它们包括但不限于会话搜索概念化(例如,Azzopardi等人[2018],Deldjoo等人[2021],Radlinski和Craswell[2017]),有效的会话查询重写(例如,Yu等人[2020]),生成和选择澄清问题(例如,Zamani等人[2020a, c]),会话偏好引出(例如,Radlinski等人[2019]和Zhang等人[2018]),以及理解用户与口语会话系统的交互(例如,Trippas et al.[2018,2020])。最近越来越多的研讨会(例如,Anand等人[2020])、研讨会(例如,Arguello等人[2018]、Burtsev等人[2017]、Chuklin等人[2018])补充了该领域不断增长的工作
{"title":"Conversational Search and Recommendation: Introduction to the Special Issue","authors":"C. Hauff, Julia Kiseleva, M. Sanderson, Hamed Zamani, Yongfeng Zhang","doi":"10.1145/3465272","DOIUrl":"https://doi.org/10.1145/3465272","url":null,"abstract":"While conversational search and recommendation has roots in early Information Retrieval (IR) research, the recent advances in automatic voice recognition and conversational agents have created increasing interest in this area. This topic was recognized as an emerging research area in the Third Strategic Workshop on Information Retrieval in Lorne (SWIRL 2018) [Culpepper et al. 2018]. Conversational search and recommendation systems consist of multiple components, from user modeling to conversational understanding to query modeling to result presentation. In recent years, the IR and related communities have witnessed a number of major contributions to the field of conversational search and recommendation. They include but are not limited to conversational search conceptualization (e.g., Azzopardi et al. [2018], Deldjoo et al. [2021], and Radlinski and Craswell [2017]), effective conversational query re-writing (e.g., Yu et al. [2020]), generating and selecting clarifying questions (e.g., Zamani et al. [2020a, c]), conversational preference elicitation (e.g., Radlinski et al. [2019] and Zhang et al. [2018]), and understanding user interactions with spoken conversational systems (e.g., Trippas et al. [2018, 2020]). The growing body of work in this area has been supplemented by an increasing number of recent seminars (e.g., Anand et al. [2020]), workshops (e.g., Arguello et al. [2018], Burtsev et al. [2017], Chuklin et al. [2018], and","PeriodicalId":6934,"journal":{"name":"ACM Transactions on Information Systems (TOIS)","volume":"1 1","pages":"1 - 6"},"PeriodicalIF":0.0,"publicationDate":"2021-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79811069","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 7
How Am I Doing?: Evaluating Conversational Search Systems Offline 我做得怎么样?:离线评估会话搜索系统
Pub Date : 2021-08-17 DOI: 10.1145/3451160
Aldo Lipani, Ben Carterette, Emine Yilmaz
As conversational agents like Siri and Alexa gain in popularity and use, conversation is becoming a more and more important mode of interaction for search. Conversational search shares some features with traditional search, but differs in some important respects: conversational search systems are less likely to return ranked lists of results (a SERP), more likely to involve iterated interactions, and more likely to feature longer, well-formed user queries in the form of natural language questions. Because of these differences, traditional methods for search evaluation (such as the Cranfield paradigm) do not translate easily to conversational search. In this work, we propose a framework for offline evaluation of conversational search, which includes a methodology for creating test collections with relevance judgments, an evaluation measure based on a user interaction model, and an approach to collecting user interaction data to train the model. The framework is based on the idea of “subtopics”, often used to model novelty and diversity in search and recommendation, and the user model is similar to the geometric browsing model introduced by RBP and used in ERR. As far as we know, this is the first work to combine these ideas into a comprehensive framework for offline evaluation of conversational search.
随着Siri和Alexa等对话代理的普及和使用,对话正成为搜索中越来越重要的交互模式。会话搜索与传统搜索共享一些特性,但在一些重要方面有所不同:会话搜索系统不太可能返回排序结果列表(SERP),更可能涉及迭代交互,并且更可能以自然语言问题的形式提供较长、格式良好的用户查询。由于这些差异,传统的搜索评估方法(如克兰菲尔德范式)不容易转化为会话搜索。在这项工作中,我们提出了一个离线评估会话搜索的框架,其中包括一种创建具有相关性判断的测试集的方法,一种基于用户交互模型的评估方法,以及一种收集用户交互数据以训练模型的方法。该框架基于“子主题”的思想,通常用于对搜索和推荐中的新颖性和多样性进行建模,用户模型类似于RBP引入并用于ERR的几何浏览模型。据我们所知,这是第一个将这些想法结合成一个全面的框架来评估会话搜索的工作。
{"title":"How Am I Doing?: Evaluating Conversational Search Systems Offline","authors":"Aldo Lipani, Ben Carterette, Emine Yilmaz","doi":"10.1145/3451160","DOIUrl":"https://doi.org/10.1145/3451160","url":null,"abstract":"As conversational agents like Siri and Alexa gain in popularity and use, conversation is becoming a more and more important mode of interaction for search. Conversational search shares some features with traditional search, but differs in some important respects: conversational search systems are less likely to return ranked lists of results (a SERP), more likely to involve iterated interactions, and more likely to feature longer, well-formed user queries in the form of natural language questions. Because of these differences, traditional methods for search evaluation (such as the Cranfield paradigm) do not translate easily to conversational search. In this work, we propose a framework for offline evaluation of conversational search, which includes a methodology for creating test collections with relevance judgments, an evaluation measure based on a user interaction model, and an approach to collecting user interaction data to train the model. The framework is based on the idea of “subtopics”, often used to model novelty and diversity in search and recommendation, and the user model is similar to the geometric browsing model introduced by RBP and used in ERR. As far as we know, this is the first work to combine these ideas into a comprehensive framework for offline evaluation of conversational search.","PeriodicalId":6934,"journal":{"name":"ACM Transactions on Information Systems (TOIS)","volume":"10 1","pages":"1 - 22"},"PeriodicalIF":0.0,"publicationDate":"2021-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87240254","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 33
Response Ranking with Multi-types of Deep Interactive Representations in Retrieval-based Dialogues 基于检索的对话中多类型深度交互表示的响应排序
Pub Date : 2021-08-17 DOI: 10.1145/3462207
Ruijian Xu, Chongyang Tao, Jiazhan Feng, Wei Wu, Rui Yan, Dongyan Zhao
Building an intelligent dialogue system with the ability to select a proper response according to a multi-turn context is challenging in three aspects: (1) the meaning of a context–response pair is built upon language units from multiple granularities (e.g., words, phrases, and sub-sentences, etc.); (2) local (e.g., a small window around a word) and long-range (e.g., words across the context and the response) dependencies may exist in dialogue data; and (3) the relationship between the context and the response candidate lies in multiple relevant semantic clues or relatively implicit semantic clues in some real cases. However, existing approaches usually encode the dialogue with mono-type representation and the interaction processes between the context and the response candidate are executed in a rather shallow manner, which may lead to an inadequate understanding of dialogue content and hinder the recognition of the semantic relevance between the context and response. To tackle these challenges, we propose a representation[K]-interaction[L]-matching framework that explores multiple types of deep interactive representations to build context-response matching models for response selection. Particularly, we construct different types of representations for utterance–response pairs and deepen them via alternate encoding and interaction. By this means, the model can handle the relation of neighboring elements, phrasal pattern, and long-range dependencies during the representation and make a more accurate prediction through multiple layers of interactions between the context–response pair. Experiment results on three public benchmarks indicate that the proposed model significantly outperforms previous conventional context-response matching models and achieve slightly better results than the BERT model for multi-turn response selection in retrieval-based dialogue systems.
构建一个能够根据多回合上下文选择适当响应的智能对话系统在三个方面具有挑战性:(1)上下文-响应对的含义建立在多个粒度(例如,单词,短语和子句等)的语言单位上;(2)对话数据中可能存在局部依赖(例如,单词周围的小窗口)和远程依赖(例如,跨上下文和响应的单词);(3)语境与应答候选者之间的关系存在多重相关语义线索或在某些实际情况下存在相对隐式的语义线索。然而,现有的方法通常用单一类型的表示对对话进行编码,并且上下文与应答候选者之间的交互过程执行得相当肤浅,这可能导致对对话内容的理解不足,阻碍了对上下文与应答之间语义相关性的识别。为了解决这些挑战,我们提出了一个表征[K]-交互[L]-匹配框架,该框架探索了多种类型的深度交互表征,以构建用于响应选择的上下文-响应匹配模型。特别是,我们为话语-反应对构建不同类型的表征,并通过交替编码和交互加深它们。通过这种方式,该模型可以在表示过程中处理相邻元素的关系、短语模式和远程依赖关系,并通过上下文-响应对之间的多层交互进行更准确的预测。在三个公共基准上的实验结果表明,该模型明显优于传统的上下文响应匹配模型,并且在基于检索的对话系统的多回合响应选择方面比BERT模型稍好。
{"title":"Response Ranking with Multi-types of Deep Interactive Representations in Retrieval-based Dialogues","authors":"Ruijian Xu, Chongyang Tao, Jiazhan Feng, Wei Wu, Rui Yan, Dongyan Zhao","doi":"10.1145/3462207","DOIUrl":"https://doi.org/10.1145/3462207","url":null,"abstract":"Building an intelligent dialogue system with the ability to select a proper response according to a multi-turn context is challenging in three aspects: (1) the meaning of a context–response pair is built upon language units from multiple granularities (e.g., words, phrases, and sub-sentences, etc.); (2) local (e.g., a small window around a word) and long-range (e.g., words across the context and the response) dependencies may exist in dialogue data; and (3) the relationship between the context and the response candidate lies in multiple relevant semantic clues or relatively implicit semantic clues in some real cases. However, existing approaches usually encode the dialogue with mono-type representation and the interaction processes between the context and the response candidate are executed in a rather shallow manner, which may lead to an inadequate understanding of dialogue content and hinder the recognition of the semantic relevance between the context and response. To tackle these challenges, we propose a representation[K]-interaction[L]-matching framework that explores multiple types of deep interactive representations to build context-response matching models for response selection. Particularly, we construct different types of representations for utterance–response pairs and deepen them via alternate encoding and interaction. By this means, the model can handle the relation of neighboring elements, phrasal pattern, and long-range dependencies during the representation and make a more accurate prediction through multiple layers of interactions between the context–response pair. Experiment results on three public benchmarks indicate that the proposed model significantly outperforms previous conventional context-response matching models and achieve slightly better results than the BERT model for multi-turn response selection in retrieval-based dialogue systems.","PeriodicalId":6934,"journal":{"name":"ACM Transactions on Information Systems (TOIS)","volume":"17 1","pages":"1 - 28"},"PeriodicalIF":0.0,"publicationDate":"2021-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78678774","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 5
From Users’ Intentions to IF-THEN Rules in the Internet of Things 从用户意图到物联网中的IF-THEN规则
Pub Date : 2021-08-16 DOI: 10.1145/3447264
Fulvio Corno, Luigi De Russis, A. M. Roffarello
In the Internet of Things era, users are willing to personalize the joint behavior of their connected entities, i.e., smart devices and online service, by means of trigger-action rules such as “IF the entrance Nest security camera detects a movement, THEN blink the Philips Hue lamp in the kitchen.” Unfortunately, the spread of new supported technologies makes the number of possible combinations between triggers and actions continuously growing, thus motivating the need of assisting users in discovering new rules and functionality, e.g., through recommendation techniques. To this end, we present , a semantic Conversational Search and Recommendation (CSR) system able to suggest pertinent IF-THEN rules that can be easily deployed in different contexts starting from an abstract user’s need. By exploiting a conversational agent, the user can communicate her current personalization intention by specifying a set of functionality at a high level, e.g., to decrease the temperature of a room when she left it. Stemming from this input, implements a semantic recommendation process that takes into account (a) the current user’s intention, (b) the connected entities owned by the user, and (c) the user’s long-term preferences revealed by her profile. If not satisfied with the suggestions, then the user can converse with the system to provide further feedback, i.e., a short-term preference, thus allowing to provide refined recommendations that better align with the original intention. We evaluate by running different offline experiments with simulated users and real-world data. First, we test the recommendation process in different configurations, and we show that recommendation accuracy and similarity with target items increase as the interaction between the algorithm and the user proceeds. Then, we compare with other similar baseline recommender systems. Results are promising and demonstrate the effectiveness of in recommending IF-THEN rules that satisfy the current personalization intention of the user.
在物联网时代,用户愿意通过触发操作规则来个性化他们连接的实体(即智能设备和在线服务)的联合行为,例如“如果Nest入口安全摄像头检测到移动,那么就会闪烁厨房里的飞利浦Hue灯”。不幸的是,新支持技术的传播使得触发器和动作之间可能的组合数量不断增加,从而激发了帮助用户发现新规则和功能的需求,例如通过推荐技术。为此,我们提出了一个语义会话搜索和推荐(CSR)系统,该系统能够建议相关的IF-THEN规则,这些规则可以从抽象的用户需求开始,轻松地部署在不同的上下文中。通过利用会话代理,用户可以通过在高层次上指定一组功能来传达她当前的个性化意图,例如,当她离开房间时降低房间的温度。基于这个输入,实现了一个语义推荐过程,该过程考虑了(a)当前用户的意图,(b)用户拥有的连接实体,以及(c)用户个人资料显示的长期偏好。如果对建议不满意,那么用户可以与系统交谈以提供进一步的反馈,即短期偏好,从而允许提供更符合原始意图的改进建议。我们通过模拟用户和真实世界数据运行不同的离线实验来进行评估。首先,我们测试了不同配置下的推荐过程,结果表明,随着算法与用户交互的进行,推荐的准确性和与目标项目的相似度都在增加。然后,我们与其他类似的基线推荐系统进行比较。结果是有希望的,并且证明了在推荐满足当前用户个性化意图的IF-THEN规则方面的有效性。
{"title":"From Users’ Intentions to IF-THEN Rules in the Internet of Things","authors":"Fulvio Corno, Luigi De Russis, A. M. Roffarello","doi":"10.1145/3447264","DOIUrl":"https://doi.org/10.1145/3447264","url":null,"abstract":"In the Internet of Things era, users are willing to personalize the joint behavior of their connected entities, i.e., smart devices and online service, by means of trigger-action rules such as “IF the entrance Nest security camera detects a movement, THEN blink the Philips Hue lamp in the kitchen.” Unfortunately, the spread of new supported technologies makes the number of possible combinations between triggers and actions continuously growing, thus motivating the need of assisting users in discovering new rules and functionality, e.g., through recommendation techniques. To this end, we present , a semantic Conversational Search and Recommendation (CSR) system able to suggest pertinent IF-THEN rules that can be easily deployed in different contexts starting from an abstract user’s need. By exploiting a conversational agent, the user can communicate her current personalization intention by specifying a set of functionality at a high level, e.g., to decrease the temperature of a room when she left it. Stemming from this input, implements a semantic recommendation process that takes into account (a) the current user’s intention, (b) the connected entities owned by the user, and (c) the user’s long-term preferences revealed by her profile. If not satisfied with the suggestions, then the user can converse with the system to provide further feedback, i.e., a short-term preference, thus allowing to provide refined recommendations that better align with the original intention. We evaluate by running different offline experiments with simulated users and real-world data. First, we test the recommendation process in different configurations, and we show that recommendation accuracy and similarity with target items increase as the interaction between the algorithm and the user proceeds. Then, we compare with other similar baseline recommender systems. Results are promising and demonstrate the effectiveness of in recommending IF-THEN rules that satisfy the current personalization intention of the user.","PeriodicalId":6934,"journal":{"name":"ACM Transactions on Information Systems (TOIS)","volume":"26 1","pages":"1 - 33"},"PeriodicalIF":0.0,"publicationDate":"2021-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85498151","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 17
MyrrorBot: A Digital Assistant Based on Holistic User Models for Personalized Access to Online Services MyrrorBot:一个基于整体用户模型的数字助理,用于个性化访问在线服务
Pub Date : 2021-08-16 DOI: 10.1145/3447679
C. Musto, F. Narducci, Marco Polignano, M. Degemmis, P. Lops, G. Semeraro
In this article, we present MyrrorBot, a personal digital assistant implementing a natural language interface that allows the users to: (i) access online services, such as music, video, news, andfood recommendations, in a personalized way, by exploiting a strategy for implicit user modeling called holistic user profiling; (ii) query their own user models, to inspect the features encoded in their profiles and to increase their awareness of the personalization process. Basically, the system allows the users to formulate natural language requests related to their information needs. Such needs are roughly classified in two groups: quantified self-related needs (e.g., Did I sleep enough? Am I extrovert?) and personalized access to online services (e.g., Play a song I like). The intent recognition strategy implemented in the platform automatically identifies the intent expressed by the user and forwards the request to specific services and modules that generate an appropriate answer that fulfills the query. In the experimental evaluation, we evaluated both qualitative (users’ acceptance of the system, usability) as well as quantitative (time required to complete basic tasks, effectiveness of the personalization strategy) aspects of the system, and the results showed that MyrrorBot can improve the way people access online services and applications. This leads to a more effective interaction and paves the way for further development of our system.
在本文中,我们介绍了MyrrorBot,一个实现自然语言界面的个人数字助理,允许用户:(i)通过利用一种称为整体用户分析的隐式用户建模策略,以个性化的方式访问在线服务,如音乐、视频、新闻和食物推荐;(ii)查询他们自己的用户模型,检查他们的配置文件中编码的特征,并提高他们对个性化过程的认识。基本上,该系统允许用户制定与他们的信息需求相关的自然语言请求。这些需求大致分为两类:量化的自我相关需求(例如,我睡得够吗?我性格外向吗?)以及个性化的在线服务(例如,播放我喜欢的歌曲)。平台中实现的意图识别策略自动识别用户表达的意图,并将请求转发给特定的服务和模块,这些服务和模块生成满足查询的适当答案。在实验评估中,我们对系统的定性(用户对系统的接受程度、可用性)和定量(完成基本任务所需的时间、个性化策略的有效性)两方面进行了评估,结果表明,MyrrorBot可以改善人们访问在线服务和应用程序的方式。这将导致更有效的互动,并为我们系统的进一步发展铺平道路。
{"title":"MyrrorBot: A Digital Assistant Based on Holistic User Models for Personalized Access to Online Services","authors":"C. Musto, F. Narducci, Marco Polignano, M. Degemmis, P. Lops, G. Semeraro","doi":"10.1145/3447679","DOIUrl":"https://doi.org/10.1145/3447679","url":null,"abstract":"In this article, we present MyrrorBot, a personal digital assistant implementing a natural language interface that allows the users to: (i) access online services, such as music, video, news, andfood recommendations, in a personalized way, by exploiting a strategy for implicit user modeling called holistic user profiling; (ii) query their own user models, to inspect the features encoded in their profiles and to increase their awareness of the personalization process. Basically, the system allows the users to formulate natural language requests related to their information needs. Such needs are roughly classified in two groups: quantified self-related needs (e.g., Did I sleep enough? Am I extrovert?) and personalized access to online services (e.g., Play a song I like). The intent recognition strategy implemented in the platform automatically identifies the intent expressed by the user and forwards the request to specific services and modules that generate an appropriate answer that fulfills the query. In the experimental evaluation, we evaluated both qualitative (users’ acceptance of the system, usability) as well as quantitative (time required to complete basic tasks, effectiveness of the personalization strategy) aspects of the system, and the results showed that MyrrorBot can improve the way people access online services and applications. This leads to a more effective interaction and paves the way for further development of our system.","PeriodicalId":6934,"journal":{"name":"ACM Transactions on Information Systems (TOIS)","volume":"15 1","pages":"1 - 34"},"PeriodicalIF":0.0,"publicationDate":"2021-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84196722","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 8
Theories of Conversation for Conversational IR 会话IR的会话理论
Pub Date : 2021-08-16 DOI: 10.1145/3439869
Paul Thomas, M. Czerwinski, Daniel J. McDuff, Nick Craswell
Conversational information retrieval is a relatively new and fast-developing research area, but conversation itself has been well studied for decades. Researchers have analysed linguistic phenomena such as structure and semantics but also paralinguistic features such as tone, body language, and even the physiological states of interlocutors. We tend to treat computers as social agents—especially if they have some humanlike features in their design—and so work from human-to-human conversation is highly relevant to how we think about the design of human-to-computer applications. In this article, we summarise some salient past work, focusing on social norms; structures; and affect, prosody, and style. We examine social communication theories briefly as a review to see what we have learned about how humans interact with each other and how that might pertain to agents and robots. We also discuss some implications for research and design of conversational IR systems.
会话信息检索是一个相对较新的快速发展的研究领域,但会话本身已经被研究了几十年。研究人员不仅分析了语言现象,如结构和语义,还分析了副语言特征,如语气、肢体语言,甚至对话者的生理状态。我们倾向于将计算机视为社会代理——特别是如果它们在设计上具有一些类似人类的特征——因此,人与人之间的对话与我们如何思考人机应用程序的设计高度相关。在本文中,我们总结了一些突出的过去的工作,重点是社会规范;结构;还有影响,韵律和风格。我们对社会沟通理论进行了简要的回顾,看看我们对人类如何相互作用以及这如何适用于代理和机器人有什么了解。我们还讨论了会话式红外系统研究和设计的一些启示。
{"title":"Theories of Conversation for Conversational IR","authors":"Paul Thomas, M. Czerwinski, Daniel J. McDuff, Nick Craswell","doi":"10.1145/3439869","DOIUrl":"https://doi.org/10.1145/3439869","url":null,"abstract":"Conversational information retrieval is a relatively new and fast-developing research area, but conversation itself has been well studied for decades. Researchers have analysed linguistic phenomena such as structure and semantics but also paralinguistic features such as tone, body language, and even the physiological states of interlocutors. We tend to treat computers as social agents—especially if they have some humanlike features in their design—and so work from human-to-human conversation is highly relevant to how we think about the design of human-to-computer applications. In this article, we summarise some salient past work, focusing on social norms; structures; and affect, prosody, and style. We examine social communication theories briefly as a review to see what we have learned about how humans interact with each other and how that might pertain to agents and robots. We also discuss some implications for research and design of conversational IR systems.","PeriodicalId":6934,"journal":{"name":"ACM Transactions on Information Systems (TOIS)","volume":"1 1","pages":"1 - 23"},"PeriodicalIF":0.0,"publicationDate":"2021-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90261800","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 18
A Graph-Based Approach for Mitigating Multi-Sided Exposure Bias in Recommender Systems 一种基于图的缓解推荐系统中多方曝光偏差的方法
Pub Date : 2021-07-07 DOI: 10.1145/3470948
M. Mansoury, Himan Abdollahpouri, Mykola Pechenizkiy, B. Mobasher, R. Burke
Fairness is a critical system-level objective in recommender systems that has been the subject of extensive recent research. A specific form of fairness is supplier exposure fairness, where the objective is to ensure equitable coverage of items across all suppliers in recommendations provided to users. This is especially important in multistakeholder recommendation scenarios where it may be important to optimize utilities not just for the end user but also for other stakeholders such as item sellers or producers who desire a fair representation of their items. This type of supplier fairness is sometimes accomplished by attempting to increase aggregate diversity to mitigate popularity bias and to improve the coverage of long-tail items in recommendations. In this article, we introduce FairMatch, a general graph-based algorithm that works as a post-processing approach after recommendation generation to improve exposure fairness for items and suppliers. The algorithm iteratively adds high-quality items that have low visibility or items from suppliers with low exposure to the users’ final recommendation lists. A comprehensive set of experiments on two datasets and comparison with state-of-the-art baselines show that FairMatch, although it significantly improves exposure fairness and aggregate diversity, maintains an acceptable level of relevance of the recommendations.
在推荐系统中,公平性是一个关键的系统级目标,也是最近广泛研究的主题。公平的一种具体形式是供应商曝光公平,其目标是确保在向用户提供的建议中公平覆盖所有供应商的产品。这在多利益相关者推荐场景中尤其重要,因为优化实用程序不仅对最终用户很重要,而且对其他利益相关者也很重要,例如希望公平地表示其物品的物品销售者或生产者。这种类型的供应商公平有时是通过尝试增加总体多样性来减轻流行偏见和提高推荐中长尾项目的覆盖率来实现的。在本文中,我们介绍了FairMatch,这是一种通用的基于图的算法,可作为推荐生成后的后处理方法,以提高商品和供应商的曝光公平性。该算法迭代地将低可见度的高质量商品或来自低曝光率供应商的商品添加到用户的最终推荐列表中。在两个数据集上进行的一组综合实验以及与最新基线的比较表明,FairMatch虽然显著提高了曝光公平性和总体多样性,但仍保持了可接受的推荐相关性水平。
{"title":"A Graph-Based Approach for Mitigating Multi-Sided Exposure Bias in Recommender Systems","authors":"M. Mansoury, Himan Abdollahpouri, Mykola Pechenizkiy, B. Mobasher, R. Burke","doi":"10.1145/3470948","DOIUrl":"https://doi.org/10.1145/3470948","url":null,"abstract":"Fairness is a critical system-level objective in recommender systems that has been the subject of extensive recent research. A specific form of fairness is supplier exposure fairness, where the objective is to ensure equitable coverage of items across all suppliers in recommendations provided to users. This is especially important in multistakeholder recommendation scenarios where it may be important to optimize utilities not just for the end user but also for other stakeholders such as item sellers or producers who desire a fair representation of their items. This type of supplier fairness is sometimes accomplished by attempting to increase aggregate diversity to mitigate popularity bias and to improve the coverage of long-tail items in recommendations. In this article, we introduce FairMatch, a general graph-based algorithm that works as a post-processing approach after recommendation generation to improve exposure fairness for items and suppliers. The algorithm iteratively adds high-quality items that have low visibility or items from suppliers with low exposure to the users’ final recommendation lists. A comprehensive set of experiments on two datasets and comparison with state-of-the-art baselines show that FairMatch, although it significantly improves exposure fairness and aggregate diversity, maintains an acceptable level of relevance of the recommendations.","PeriodicalId":6934,"journal":{"name":"ACM Transactions on Information Systems (TOIS)","volume":"68 1","pages":"1 - 31"},"PeriodicalIF":0.0,"publicationDate":"2021-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86060692","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 28
期刊
ACM Transactions on Information Systems (TOIS)
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
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
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1