{"title":"Session details: Session 6A: Social Media","authors":"J. Mothe","doi":"10.1145/3349689","DOIUrl":"https://doi.org/10.1145/3349689","url":null,"abstract":"","PeriodicalId":20700,"journal":{"name":"Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval","volume":"221 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72578140","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}
Diksha Garg, Priyanka Gupta, Pankaj Malhotra, L. Vig, Gautam M. Shroff
Recent advances in sequence-aware approaches for session-based recommendation, such as those based on recurrent neural networks, highlight the importance of leveraging sequential information from a session while making recommendations. Further, a session based k-nearest-neighbors approach (SKNN) has proven to be a strong baseline for session-based recommendations. However, SKNN does not take into account the readily available sequential and temporal information from sessions. In this work, we propose Sequence and Time Aware Neighborhood (STAN), with vanilla SKNN as its special case. STAN takes into account the following factors for making recommendations: i) position of an item in the current session, ii) recency of a past session w.r.t. to the current session, and iii) position of a recommendable item in a neighboring session. The importance of above factors for a specific application can be adjusted via controllable decay factors. Despite being simple, intuitive and easy to implement, empirical evaluation on three real-world datasets shows that STAN significantly improves over SKNN, and is even comparable to the recently proposed state-of-the-art deep learning approaches. Our results suggest that STAN can be considered as a strong baseline for evaluating session-based recommendation algorithms in future.
{"title":"Sequence and Time Aware Neighborhood for Session-based Recommendations: STAN","authors":"Diksha Garg, Priyanka Gupta, Pankaj Malhotra, L. Vig, Gautam M. Shroff","doi":"10.1145/3331184.3331322","DOIUrl":"https://doi.org/10.1145/3331184.3331322","url":null,"abstract":"Recent advances in sequence-aware approaches for session-based recommendation, such as those based on recurrent neural networks, highlight the importance of leveraging sequential information from a session while making recommendations. Further, a session based k-nearest-neighbors approach (SKNN) has proven to be a strong baseline for session-based recommendations. However, SKNN does not take into account the readily available sequential and temporal information from sessions. In this work, we propose Sequence and Time Aware Neighborhood (STAN), with vanilla SKNN as its special case. STAN takes into account the following factors for making recommendations: i) position of an item in the current session, ii) recency of a past session w.r.t. to the current session, and iii) position of a recommendable item in a neighboring session. The importance of above factors for a specific application can be adjusted via controllable decay factors. Despite being simple, intuitive and easy to implement, empirical evaluation on three real-world datasets shows that STAN significantly improves over SKNN, and is even comparable to the recently proposed state-of-the-art deep learning approaches. Our results suggest that STAN can be considered as a strong baseline for evaluating session-based recommendation algorithms in future.","PeriodicalId":20700,"journal":{"name":"Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval","volume":"67 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72644553","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}
Sound effects play an essential role in producing high-quality radio stories but require enormous labor cost to add. In this paper, we address the problem of automatically adding sound effects to radio stories with a retrieval-based model. However, directly implementing a tag-based retrieval model leads to high false positives due to the ambiguity of story contents. To solve this problem, we introduce a retrieval-based framework hybridized with a semantic inference model which helps to achieve robust retrieval results. Our model relies on fine-designed features extracted from the context of candidate triggers. We collect two story dubbing datasets through crowdsourcing to analyze the setting of adding sound effects and to train and test our proposed methods. We further discuss the importance of each feature and introduce several heuristic rules for the trade-off between precision and recall. Together with the text-to-speech technology, our results reveal a promising automatic pipeline on producing high-quality radio stories.
{"title":"From Text to Sound: A Preliminary Study on Retrieving Sound Effects to Radio Stories","authors":"Songwei Ge, Curtis Xuan, Ruihua Song, Chao Zou, Wei Liu, Jin Zhou","doi":"10.1145/3331184.3331274","DOIUrl":"https://doi.org/10.1145/3331184.3331274","url":null,"abstract":"Sound effects play an essential role in producing high-quality radio stories but require enormous labor cost to add. In this paper, we address the problem of automatically adding sound effects to radio stories with a retrieval-based model. However, directly implementing a tag-based retrieval model leads to high false positives due to the ambiguity of story contents. To solve this problem, we introduce a retrieval-based framework hybridized with a semantic inference model which helps to achieve robust retrieval results. Our model relies on fine-designed features extracted from the context of candidate triggers. We collect two story dubbing datasets through crowdsourcing to analyze the setting of adding sound effects and to train and test our proposed methods. We further discuss the importance of each feature and introduce several heuristic rules for the trade-off between precision and recall. Together with the text-to-speech technology, our results reveal a promising automatic pipeline on producing high-quality radio stories.","PeriodicalId":20700,"journal":{"name":"Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval","volume":"3 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74648903","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}
Xin Zhou, Yating Zhang, Xiaozhong Liu, Changlong Sun, Luo Si
Various e-commerce platforms produce millions of transactions per day with many transaction disputes. This generates the demand for effective and efficient dispute resolutions for e-commerce transactions. This paper proposes a novel research task of Legal Dispute Judgment (LDJ) prediction for e-commerce transactions, which connects two yet isolated domains, e-commerce data mining and legal intelligence. Different from traditional legal intelligence with the focus on textual evidence of the dispute itself, the new research utilizes multiview information such as past behavior information of seller and buyer as well as textual evidence of the current transaction. The multiview dispute representation is integrated into an innovative multi-task learning framework for predicting the legal result. An extensive set of experiments with a large dispute case dataset collected from a world leading e-commerce platform shows that the proposed model can more accurately characterize a dispute case through buyer, seller, and transaction viewpoints for legal judgment prediction against several alternatives.
{"title":"Legal Intelligence for E-commerce: Multi-task Learning by Leveraging Multiview Dispute Representation","authors":"Xin Zhou, Yating Zhang, Xiaozhong Liu, Changlong Sun, Luo Si","doi":"10.1145/3331184.3331212","DOIUrl":"https://doi.org/10.1145/3331184.3331212","url":null,"abstract":"Various e-commerce platforms produce millions of transactions per day with many transaction disputes. This generates the demand for effective and efficient dispute resolutions for e-commerce transactions. This paper proposes a novel research task of Legal Dispute Judgment (LDJ) prediction for e-commerce transactions, which connects two yet isolated domains, e-commerce data mining and legal intelligence. Different from traditional legal intelligence with the focus on textual evidence of the dispute itself, the new research utilizes multiview information such as past behavior information of seller and buyer as well as textual evidence of the current transaction. The multiview dispute representation is integrated into an innovative multi-task learning framework for predicting the legal result. An extensive set of experiments with a large dispute case dataset collected from a world leading e-commerce platform shows that the proposed model can more accurately characterize a dispute case through buyer, seller, and transaction viewpoints for legal judgment prediction against several alternatives.","PeriodicalId":20700,"journal":{"name":"Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval","volume":"46 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75007716","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}
We revisit the Normalized Query Commitment (NQC) query performance prediction (QPP) method. To this end, we suggest a scaled extension to a discriminative QPP framework and use it to analyze NQC. Using this analysis allows us to redesign NQC and suggest several options for improvement.
{"title":"Normalized Query Commitment Revisited","authors":"Haggai Roitman","doi":"10.1145/3331184.3331334","DOIUrl":"https://doi.org/10.1145/3331184.3331334","url":null,"abstract":"We revisit the Normalized Query Commitment (NQC) query performance prediction (QPP) method. To this end, we suggest a scaled extension to a discriminative QPP framework and use it to analyze NQC. Using this analysis allows us to redesign NQC and suggest several options for improvement.","PeriodicalId":20700,"journal":{"name":"Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval","volume":"15 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74084262","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}
At Ancestry, we apply learning to rank algorithms to a new area to assist our customers in better understanding their family history. The foundation of our service is an extensive and unique collection of billions of historical records that we have digitized and indexed. Currently, our content collection includes 20 billion historical records. The record data consists of birth records, death records, marriage records, adoption records, census records, obituary records, among many others types. It is important for us to return relevant records from diversified record types in order to assist our customers to better understand their family history.
{"title":"Family History Discovery through Search at Ancestry","authors":"Peng Jiang, Yingrui Yang, Gann Bierner, F. Li, Ruhan Wang, Azadeh Moghtaderi","doi":"10.1145/3331184.3331430","DOIUrl":"https://doi.org/10.1145/3331184.3331430","url":null,"abstract":"At Ancestry, we apply learning to rank algorithms to a new area to assist our customers in better understanding their family history. The foundation of our service is an extensive and unique collection of billions of historical records that we have digitized and indexed. Currently, our content collection includes 20 billion historical records. The record data consists of birth records, death records, marriage records, adoption records, census records, obituary records, among many others types. It is important for us to return relevant records from diversified record types in order to assist our customers to better understand their family history.","PeriodicalId":20700,"journal":{"name":"Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval","volume":"75 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75070138","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}
The tutorial is based on our long-term research on open domain conversation, rich hands-on experience on development of Microsoft XiaoIce, and our previous tutorials on EMNLP 2018 and the Web Conference 2019. It starts from a summary of recent achievement made by both academia and industry on chatbots, and then performs a thorough and systematic introduction to state-of-the-art methods for open domain conversation modeling including both retrieval-based methods and generation-based methods. In addition to these, the tutorial also covers some new progress on both groups of methods, such as transition from model design to model learning, transition from knowledge agnostic conversation to knowledge aware conversation, and transition from single-modal conversation to multi-modal conversation. The tutorial is ended by some promising future directions such as how to combine non-task-oriented dialogue systems with task-oriented dialogue systems and how to enhance language learning with chatbots.
{"title":"Deep Chit-Chat: Deep Learning for Chatbots","authors":"Wei Wu, Rui Yan","doi":"10.1145/3331184.3331388","DOIUrl":"https://doi.org/10.1145/3331184.3331388","url":null,"abstract":"The tutorial is based on our long-term research on open domain conversation, rich hands-on experience on development of Microsoft XiaoIce, and our previous tutorials on EMNLP 2018 and the Web Conference 2019. It starts from a summary of recent achievement made by both academia and industry on chatbots, and then performs a thorough and systematic introduction to state-of-the-art methods for open domain conversation modeling including both retrieval-based methods and generation-based methods. In addition to these, the tutorial also covers some new progress on both groups of methods, such as transition from model design to model learning, transition from knowledge agnostic conversation to knowledge aware conversation, and transition from single-modal conversation to multi-modal conversation. The tutorial is ended by some promising future directions such as how to combine non-task-oriented dialogue systems with task-oriented dialogue systems and how to enhance language learning with chatbots.","PeriodicalId":20700,"journal":{"name":"Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval","volume":"232 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72896521","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}
G. Cormack, Haotian Zhang, Nimesh Ghelani, Mustafa Abualsaud, Mark D. Smucker, Maura R. Grossman, Shahin Rahbariasl, Amira Ghenai
A team of six assessors used Dynamic Sampling (Cormack and Grossman 2018) and one hour of assessment effort per topic to form, without pooling, a test collection for the TREC 2018 Common Core Track. Later, official relevance assessments were rendered by NIST for documents selected by depth-10 pooling augmented by move-to-front (MTF) pooling (Cormack et al. 1998), as well as the documents selected by our Dynamic Sampling effort. MAP estimates rendered from dynamically sampled assessments using the xinfAP statistical evaluator are comparable to those rendered from the complete set of official assessments using the standard trec_eval tool. MAP estimates rendered using only documents selected by pooling, on the other hand, differ substantially. The results suggest that the use of Dynamic Sampling without pooling can, for an order of magnitude less assessment effort, yield information-retrieval effectiveness estimates that exhibit lower bias, lower error, and comparable ability to rank system effectiveness.
一个由六名评估人员组成的团队使用动态抽样(Cormack和Grossman 2018)和每个主题一小时的评估工作，形成TREC 2018年共同核心轨道的测试集合，而不是汇集。后来，NIST对深度-10池选择的通过移动到前端(MTF)池(Cormack et al. 1998)增强的文档以及我们的动态采样工作选择的文档进行了官方相关性评估。使用xinfAP统计评估器从动态采样评估中呈现的MAP估计与使用标准tre_eval工具从完整的官方评估集呈现的MAP估计相当。另一方面，仅使用池选择的文档呈现的MAP估计有很大不同。结果表明，使用没有池化的动态抽样可以在一个数量级上减少评估工作，产生具有更低偏差、更低误差的信息检索有效性估计，并具有对系统有效性排序的可比较能力。
{"title":"Dynamic Sampling Meets Pooling","authors":"G. Cormack, Haotian Zhang, Nimesh Ghelani, Mustafa Abualsaud, Mark D. Smucker, Maura R. Grossman, Shahin Rahbariasl, Amira Ghenai","doi":"10.1145/3331184.3331354","DOIUrl":"https://doi.org/10.1145/3331184.3331354","url":null,"abstract":"A team of six assessors used Dynamic Sampling (Cormack and Grossman 2018) and one hour of assessment effort per topic to form, without pooling, a test collection for the TREC 2018 Common Core Track. Later, official relevance assessments were rendered by NIST for documents selected by depth-10 pooling augmented by move-to-front (MTF) pooling (Cormack et al. 1998), as well as the documents selected by our Dynamic Sampling effort. MAP estimates rendered from dynamically sampled assessments using the xinfAP statistical evaluator are comparable to those rendered from the complete set of official assessments using the standard trec_eval tool. MAP estimates rendered using only documents selected by pooling, on the other hand, differ substantially. The results suggest that the use of Dynamic Sampling without pooling can, for an order of magnitude less assessment effort, yield information-retrieval effectiveness estimates that exhibit lower bias, lower error, and comparable ability to rank system effectiveness.","PeriodicalId":20700,"journal":{"name":"Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72933854","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}
{"title":"Session details: Session 1B: Health and Social Media","authors":"Mark D. Smucker","doi":"10.1145/3349676","DOIUrl":"https://doi.org/10.1145/3349676","url":null,"abstract":"","PeriodicalId":20700,"journal":{"name":"Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval","volume":"30 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90301308","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}
Cen Chen, Chilin Fu, Xujun Hu, Xiaolu Zhang, Jun Zhou, Xiaolong Li, F. S. Bao
A customer service bot is now a necessary component of an e-commerce platform. As a core module of the customer service bot, user intent prediction can help predict user questions before they ask. A typical solution is to find top candidate questions that a user will be interested in. Such solution ignores the inter-relationship between questions and often aims to maximize the immediate reward such as clicks, which may not be ideal in practice. Hence, we propose to view the problem as a sequential decision making process to better capture the long-term effects of each recommendation in the list. Intuitively, we formulate the problem as a Markov decision process and consider using reinforcement learning for the problem. With this approach, questions presented to users are both relevant and diverse. Experiments on offline real-world dataset and online system demonstrate the effectiveness of our proposed approach.
{"title":"Reinforcement Learning for User Intent Prediction in Customer Service Bots","authors":"Cen Chen, Chilin Fu, Xujun Hu, Xiaolu Zhang, Jun Zhou, Xiaolong Li, F. S. Bao","doi":"10.1145/3331184.3331370","DOIUrl":"https://doi.org/10.1145/3331184.3331370","url":null,"abstract":"A customer service bot is now a necessary component of an e-commerce platform. As a core module of the customer service bot, user intent prediction can help predict user questions before they ask. A typical solution is to find top candidate questions that a user will be interested in. Such solution ignores the inter-relationship between questions and often aims to maximize the immediate reward such as clicks, which may not be ideal in practice. Hence, we propose to view the problem as a sequential decision making process to better capture the long-term effects of each recommendation in the list. Intuitively, we formulate the problem as a Markov decision process and consider using reinforcement learning for the problem. With this approach, questions presented to users are both relevant and diverse. Experiments on offline real-world dataset and online system demonstrate the effectiveness of our proposed approach.","PeriodicalId":20700,"journal":{"name":"Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval","volume":"12 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81381496","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：