S. Da Col, Radu Ciucanu, Marta Soare, Nassim Bouarour, Sihem Amer-Yahia
Data summarization provides a bird's eye view of data and groupby queries have been the method of choice for data summarization. Such queries provide the ability to group by some attributes and aggregate by others, and their results can be coupled with a visualization to convey insights. The number of possible groupbys that can be computed over a dataset is quite large which naturally calls for developing approaches to aid users in choosing which groupbys best summarize data. We demonstrate DashBot, a system that leverages Machine Learning to guide users in generating data-driven and customized dashboards. A dashboard contains a set of panels, each of which is a groupby query. DashBot iteratively recommends the most relevant panel while ensuring coverage. Relevance is computed based on intrinsic measures of the dataset and coverage aims to provide comprehensive summaries. DashBot relies on a Multi-Armed Bandits (MABs) approach to balance exploitation of relevance and exploration of different regions of the data to achieve coverage. Users can provide feedback and explanations to customize recommended panels. We demonstrate the utility and features of DashBot on different datasets.
{"title":"DashBot","authors":"S. Da Col, Radu Ciucanu, Marta Soare, Nassim Bouarour, Sihem Amer-Yahia","doi":"10.1145/3459637.3481968","DOIUrl":"https://doi.org/10.1145/3459637.3481968","url":null,"abstract":"Data summarization provides a bird's eye view of data and groupby queries have been the method of choice for data summarization. Such queries provide the ability to group by some attributes and aggregate by others, and their results can be coupled with a visualization to convey insights. The number of possible groupbys that can be computed over a dataset is quite large which naturally calls for developing approaches to aid users in choosing which groupbys best summarize data. We demonstrate DashBot, a system that leverages Machine Learning to guide users in generating data-driven and customized dashboards. A dashboard contains a set of panels, each of which is a groupby query. DashBot iteratively recommends the most relevant panel while ensuring coverage. Relevance is computed based on intrinsic measures of the dataset and coverage aims to provide comprehensive summaries. DashBot relies on a Multi-Armed Bandits (MABs) approach to balance exploitation of relevance and exploration of different regions of the data to achieve coverage. Users can provide feedback and explanations to customize recommended panels. We demonstrate the utility and features of DashBot on different datasets.","PeriodicalId":405296,"journal":{"name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","volume":"12 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134363027","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}
Qiong Nan, Juan Cao, Yongchun Zhu, Yanyan Wang, Jintao Li
Fake news spread widely on social media in various domains, which lead to real-world threats in many aspects like politics, disasters, and finance. Most existing approaches focus on single-domain fake news detection (SFND), which leads to unsatisfying performance when these methods are applied to multi-domain fake news detection. As an emerging field, multi-domain fake news detection (MFND) is increasingly attracting attention. However, data distributions, such as word frequency and propagation patterns, vary from domain to domain, namely domain shift. Facing the challenge of serious domain shift, existing fake news detection techniques perform poorly for multi-domain scenarios. Therefore, it is demanding to design a specialized model for MFND. In this paper, we first design a benchmark of fake news dataset for MFDN with domain label annotated, namely Weibo21, which consists of 4,488 fake news and 4,640 real news from 9 different domains. We further propose an effective Multi-domain Fake News Detection Model (MDFEND) by utilizing domain gate to aggregate multiple representations extracted by a mixture of experts. The experiments show that MDFEND can significantly improve the performance of multi-domain fake news detection. Our dataset and code are available at https://github.com/kennqiang/MDFEND-Weibo21.
{"title":"MDFEND: Multi-domain Fake News Detection","authors":"Qiong Nan, Juan Cao, Yongchun Zhu, Yanyan Wang, Jintao Li","doi":"10.1145/3459637.3482139","DOIUrl":"https://doi.org/10.1145/3459637.3482139","url":null,"abstract":"Fake news spread widely on social media in various domains, which lead to real-world threats in many aspects like politics, disasters, and finance. Most existing approaches focus on single-domain fake news detection (SFND), which leads to unsatisfying performance when these methods are applied to multi-domain fake news detection. As an emerging field, multi-domain fake news detection (MFND) is increasingly attracting attention. However, data distributions, such as word frequency and propagation patterns, vary from domain to domain, namely domain shift. Facing the challenge of serious domain shift, existing fake news detection techniques perform poorly for multi-domain scenarios. Therefore, it is demanding to design a specialized model for MFND. In this paper, we first design a benchmark of fake news dataset for MFDN with domain label annotated, namely Weibo21, which consists of 4,488 fake news and 4,640 real news from 9 different domains. We further propose an effective Multi-domain Fake News Detection Model (MDFEND) by utilizing domain gate to aggregate multiple representations extracted by a mixture of experts. The experiments show that MDFEND can significantly improve the performance of multi-domain fake news detection. Our dataset and code are available at https://github.com/kennqiang/MDFEND-Weibo21.","PeriodicalId":405296,"journal":{"name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134434889","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}
Static malware detection is important for protection against malware by allowing for malicious files to be detected prior to execution. It is also especially suitable for machine learning-based approaches. Recently, gradient boosting decision trees (GBDT) models, e.g., LightGBM (a popular implementation of GBDT), have shown outstanding performance for malware detection. However, as malware programs are known to evolve rapidly, malware classification models trained on the (source) training data often fail to generalize to the target domain, i.e., the deployed environment. To handle the underlying data distribution drifts, unsupervised domain adaptation techniques have been proposed for machine learning models including deep learning models. However, unsupervised domain adaptation for GBDT has remained challenging. In this paper, we adapt the adversarial learning framework for unsupervised domain adaptation to enable GBDT learn domain-invariant features and alleviate performance degradation in the target domain. In addition, to fully exploit the unlabelled target data, we merge them into the training dataset after pseudo-labelling. We propose a new weighting scheme integrated into GBDT for sampling instances in each boosting round to reduce the negative impact of wrongly labelled target instances. Experiments on two large malware datasets demonstrate the superiority of our proposed method.
{"title":"Unsupervised Domain Adaptation for Static Malware Detection based on Gradient Boosting Trees","authors":"Panpan Qi, Wei Wang, Lei Zhu, See-Kiong Ng","doi":"10.1145/3459637.3482400","DOIUrl":"https://doi.org/10.1145/3459637.3482400","url":null,"abstract":"Static malware detection is important for protection against malware by allowing for malicious files to be detected prior to execution. It is also especially suitable for machine learning-based approaches. Recently, gradient boosting decision trees (GBDT) models, e.g., LightGBM (a popular implementation of GBDT), have shown outstanding performance for malware detection. However, as malware programs are known to evolve rapidly, malware classification models trained on the (source) training data often fail to generalize to the target domain, i.e., the deployed environment. To handle the underlying data distribution drifts, unsupervised domain adaptation techniques have been proposed for machine learning models including deep learning models. However, unsupervised domain adaptation for GBDT has remained challenging. In this paper, we adapt the adversarial learning framework for unsupervised domain adaptation to enable GBDT learn domain-invariant features and alleviate performance degradation in the target domain. In addition, to fully exploit the unlabelled target data, we merge them into the training dataset after pseudo-labelling. We propose a new weighting scheme integrated into GBDT for sampling instances in each boosting round to reduce the negative impact of wrongly labelled target instances. Experiments on two large malware datasets demonstrate the superiority of our proposed method.","PeriodicalId":405296,"journal":{"name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","volume":"196 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134504181","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}
André Pomp, A. Paulus, Andreas Burgdorf, Tobias Meisen
Today, smart city applications are largely based on data collected from different stakeholders. This presupposes that the required data sources are publicly available. While open data platforms already provide a number of urban data sources, enterprises and citizens have few opportunities to make their data available. To complicate things further, if the data is published, the processing of this data is already extremely time-consuming today, as the data sources are heterogeneous and the corresponding homogenization has to be carried out by the data consumers themselves. In this paper, we present a data marketplace that enables different stakeholders (public institutions, enterprises, citizens) to easily provide data that can especially contribute to the further realization of smart cities. This marketplace is based on the principles of semantic data management, i.e., data providers annotate their added data with semantic models. With the help of these models, the data sources can be found and understood by data consumers and finally homogenized in a way that is suitable for their application.
{"title":"A Semantic Data Marketplace for Easy Data Sharing within a Smart City","authors":"André Pomp, A. Paulus, Andreas Burgdorf, Tobias Meisen","doi":"10.1145/3459637.3481995","DOIUrl":"https://doi.org/10.1145/3459637.3481995","url":null,"abstract":"Today, smart city applications are largely based on data collected from different stakeholders. This presupposes that the required data sources are publicly available. While open data platforms already provide a number of urban data sources, enterprises and citizens have few opportunities to make their data available. To complicate things further, if the data is published, the processing of this data is already extremely time-consuming today, as the data sources are heterogeneous and the corresponding homogenization has to be carried out by the data consumers themselves. In this paper, we present a data marketplace that enables different stakeholders (public institutions, enterprises, citizens) to easily provide data that can especially contribute to the further realization of smart cities. This marketplace is based on the principles of semantic data management, i.e., data providers annotate their added data with semantic models. With the help of these models, the data sources can be found and understood by data consumers and finally homogenized in a way that is suitable for their application.","PeriodicalId":405296,"journal":{"name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","volume":"238 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131509292","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}
Health claims are sentences on the food product packages to claim the nutrition and the benefits of the nutrition. Consumers in different European contexts often have difficulties understanding health claims, leading to increased confusion about and decreased trust in the food they buy. Focusing on this problem, we develop a toolkit for improving the communication of health claims for consumers. The toolkit provides (1) interactive activities to disseminate knowledge about health claims to the public, and (2) an NLP-based analysis and prediction engine that food manufacturers can use to estimate how consumers like the health claims that the manufacturers created. By using the AI-powered toolkit, consumers, manufacturers, and food safety regulators are engaged in determining the different linguistic and cultural barriers to the effective communication of health claims and formulating solutions that can be implemented on multiple levels, including regulation, enforcement, marketing, and consumer education.
{"title":"Health Claims Unpacked: A toolkit to Enhance the Communication of Health Claims for Food","authors":"Xiao Li, Huizhi Liang, Zehao Liu","doi":"10.1145/3459637.3481984","DOIUrl":"https://doi.org/10.1145/3459637.3481984","url":null,"abstract":"Health claims are sentences on the food product packages to claim the nutrition and the benefits of the nutrition. Consumers in different European contexts often have difficulties understanding health claims, leading to increased confusion about and decreased trust in the food they buy. Focusing on this problem, we develop a toolkit for improving the communication of health claims for consumers. The toolkit provides (1) interactive activities to disseminate knowledge about health claims to the public, and (2) an NLP-based analysis and prediction engine that food manufacturers can use to estimate how consumers like the health claims that the manufacturers created. By using the AI-powered toolkit, consumers, manufacturers, and food safety regulators are engaged in determining the different linguistic and cultural barriers to the effective communication of health claims and formulating solutions that can be implemented on multiple levels, including regulation, enforcement, marketing, and consumer education.","PeriodicalId":405296,"journal":{"name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115908465","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}
Tree similarity join is useful for analyzing tree structured data. The traditional threshold-based tree similarity join requires a similarity threshold, which is usually a difficult task for users. To remedy this issue, we advocate the problem of top-k tree similarity join. Given a collection of trees and a parameter k, the top-k tree similarity join aims to find k tree pairs with minimum tree edit distance (TED). Although we show that this problem can be resolved by utilizing the threshold-based join, the efficiency is unsatisfactory. In this paper, we propose an efficient algorithm, namely TopKTJoin, which generates the candidate tree pairs incrementally using an inverted index. We also derive TED lower bound for the unseen tree pairs. Together with TED value of the k-th best join result seen so far, we have a chance to terminate the algorithm early without missing any correct results. To further improve the efficiency, we propose two optimization techniques in terms of index structure and verification mechanism. We conduct comprehensive performance studies on real and synthetic datasets. The experimental results demonstrate that TopKTJoin significantly outperforms the baseline method.
{"title":"Top-k Tree Similarity Join","authors":"Jianhua Wang, Jianye Yang, Wenjie Zhang","doi":"10.1145/3459637.3482304","DOIUrl":"https://doi.org/10.1145/3459637.3482304","url":null,"abstract":"Tree similarity join is useful for analyzing tree structured data. The traditional threshold-based tree similarity join requires a similarity threshold, which is usually a difficult task for users. To remedy this issue, we advocate the problem of top-k tree similarity join. Given a collection of trees and a parameter k, the top-k tree similarity join aims to find k tree pairs with minimum tree edit distance (TED). Although we show that this problem can be resolved by utilizing the threshold-based join, the efficiency is unsatisfactory. In this paper, we propose an efficient algorithm, namely TopKTJoin, which generates the candidate tree pairs incrementally using an inverted index. We also derive TED lower bound for the unseen tree pairs. Together with TED value of the k-th best join result seen so far, we have a chance to terminate the algorithm early without missing any correct results. To further improve the efficiency, we propose two optimization techniques in terms of index structure and verification mechanism. We conduct comprehensive performance studies on real and synthetic datasets. The experimental results demonstrate that TopKTJoin significantly outperforms the baseline method.","PeriodicalId":405296,"journal":{"name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134397017","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}
Clarification has attracted much attention because of its many potential applications especially in Web search. Since search queries are very short, the underlying user intents are often ambiguous. This makes it challenging for search engines to return the appropriate results that pertain to the users' actual information needs. To address this issue, asking clarifying questions has been recognized as a critical technique. Although previous studies have analyzed the importance of asking to clarify, generating clarifying questions for Web search remains under-explored. In this paper, we tackle this problem in a template-guided manner. Our objective is jointly learning to select question templates and fill question slots, using Transformer-based networks. We conduct experiments on MIMICS, a collection of datasets containing real Web search queries sampled from Bing's search logs. Our method is demonstrated to achieve significant improvements over various competitive baselines.
{"title":"Template-guided Clarifying Question Generation for Web Search Clarification","authors":"Jian Wang, Wenjie Li","doi":"10.1145/3459637.3482199","DOIUrl":"https://doi.org/10.1145/3459637.3482199","url":null,"abstract":"Clarification has attracted much attention because of its many potential applications especially in Web search. Since search queries are very short, the underlying user intents are often ambiguous. This makes it challenging for search engines to return the appropriate results that pertain to the users' actual information needs. To address this issue, asking clarifying questions has been recognized as a critical technique. Although previous studies have analyzed the importance of asking to clarify, generating clarifying questions for Web search remains under-explored. In this paper, we tackle this problem in a template-guided manner. Our objective is jointly learning to select question templates and fill question slots, using Transformer-based networks. We conduct experiments on MIMICS, a collection of datasets containing real Web search queries sampled from Bing's search logs. Our method is demonstrated to achieve significant improvements over various competitive baselines.","PeriodicalId":405296,"journal":{"name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132168450","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}
Targeted Opinion Word Extraction (TOWE) is a subtask of aspect-based sentiment analysis, which aims to identify the correspondingopinion terms for given opinion targets in a review. To solve theTOWE task, recent works mainly focus on learning the target-aware context representation that infuses target information intocontext representation by using various neural networks. However,it has been unclear how to encode the target information to BERT,a powerful pre-trained language model. In this paper, we proposea novel TOWE model, RABERT (Relation-Aware BERT), that canfully utilize BERT to obtain target-aware context representations.To introduce the target information into BERT layers clearly, wedesign a simple but effective encoding method that adds targetmarkers indicating the opinion targets to the sentence. In addi-tion, we find that the neighbor word information is also importantfor extracting the opinion terms. Therefore, RABERT employs thetarget-sentence relation network and the neighbor-aware relationnetwork to consider both the opinion target and the neighbor wordsinformation. Our experimental results on four benchmark datasetsshow that RABERT significantly outperforms the other baselinesand achieves state-of-the-art performance. We also demonstrate theeffectiveness of each component of RABERT in further analysis
{"title":"RABERT: Relation-Aware BERT for Target-Oriented Opinion Words Extraction","authors":"Taegwan Kang, Minwoo Lee, Nakyeong Yang, Kyomin Jung","doi":"10.1145/3459637.3482165","DOIUrl":"https://doi.org/10.1145/3459637.3482165","url":null,"abstract":"Targeted Opinion Word Extraction (TOWE) is a subtask of aspect-based sentiment analysis, which aims to identify the correspondingopinion terms for given opinion targets in a review. To solve theTOWE task, recent works mainly focus on learning the target-aware context representation that infuses target information intocontext representation by using various neural networks. However,it has been unclear how to encode the target information to BERT,a powerful pre-trained language model. In this paper, we proposea novel TOWE model, RABERT (Relation-Aware BERT), that canfully utilize BERT to obtain target-aware context representations.To introduce the target information into BERT layers clearly, wedesign a simple but effective encoding method that adds targetmarkers indicating the opinion targets to the sentence. In addi-tion, we find that the neighbor word information is also importantfor extracting the opinion terms. Therefore, RABERT employs thetarget-sentence relation network and the neighbor-aware relationnetwork to consider both the opinion target and the neighbor wordsinformation. Our experimental results on four benchmark datasetsshow that RABERT significantly outperforms the other baselinesand achieves state-of-the-art performance. We also demonstrate theeffectiveness of each component of RABERT in further analysis","PeriodicalId":405296,"journal":{"name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131674561","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}
With the booming of the Internet finance and e-payment business, telecom and online fraud has become a serious problem which grows rapidly. In China, 351 billion RMB (approximately 0.3% of China's GDP) was lost in 2018 due to telecommunication and online fraud, influencing tens of millions of individual customers. Anti-fraud algorithms have been widely adopted by major Internet finance companies to detect and block transactions induced by scam. However, due to limited contextual information, most systems would probably mistakenly block the normal transactions, leading to poor user experience. On the other hand, if the transactions induced by scam are detected yet not fully explained to the users, the users will continue to pay, suffering from direct financial losses. To address these problems, we design a voice-enabled bot that interacts with the customers who are involved with potential telecommunication and online frauds decided by the back-end system. The bot seeks additional information from the customers through natural conversations to confirm whether the customers are scammed and identify the actual fraud types. The details about the frauds are then provided to convince the customers that they are on the edge of being scammed. Our bot adopts offline reinforcement learning (RL) to learn dialogue policies from real-world human-human chat logs. During the conversations, our bot also identifies fraud types every turn based on the dialogue state. The bot proposed outperforms baseline dialogue strategies by 2.8% in terms of task success rate, and 5% in terms of dialogue accuracy in offline evaluations. Furthermore, in the 8 months of real-world deployment, our bot lowers the dissatisfaction rate by 25% and increases the fraud prevention rate by 135% relatively, indicating a significant improvement in user experience as well as anti-fraud effectiveness. More importantly, we help prevent millions of users from being deceived, and avoid trillions of financial losses.
{"title":"'Could You Describe the Reason for the Transfer?': A Reinforcement Learning Based Voice-Enabled Bot Protecting Customers from Financial Frauds","authors":"Zihao Wang, Fudong Wang, Haipeng Zhang, Minghui Yang, Shaosheng Cao, Zujie Wen, Zhe Zhang","doi":"10.1145/3459637.3481906","DOIUrl":"https://doi.org/10.1145/3459637.3481906","url":null,"abstract":"With the booming of the Internet finance and e-payment business, telecom and online fraud has become a serious problem which grows rapidly. In China, 351 billion RMB (approximately 0.3% of China's GDP) was lost in 2018 due to telecommunication and online fraud, influencing tens of millions of individual customers. Anti-fraud algorithms have been widely adopted by major Internet finance companies to detect and block transactions induced by scam. However, due to limited contextual information, most systems would probably mistakenly block the normal transactions, leading to poor user experience. On the other hand, if the transactions induced by scam are detected yet not fully explained to the users, the users will continue to pay, suffering from direct financial losses. To address these problems, we design a voice-enabled bot that interacts with the customers who are involved with potential telecommunication and online frauds decided by the back-end system. The bot seeks additional information from the customers through natural conversations to confirm whether the customers are scammed and identify the actual fraud types. The details about the frauds are then provided to convince the customers that they are on the edge of being scammed. Our bot adopts offline reinforcement learning (RL) to learn dialogue policies from real-world human-human chat logs. During the conversations, our bot also identifies fraud types every turn based on the dialogue state. The bot proposed outperforms baseline dialogue strategies by 2.8% in terms of task success rate, and 5% in terms of dialogue accuracy in offline evaluations. Furthermore, in the 8 months of real-world deployment, our bot lowers the dissatisfaction rate by 25% and increases the fraud prevention rate by 135% relatively, indicating a significant improvement in user experience as well as anti-fraud effectiveness. More importantly, we help prevent millions of users from being deceived, and avoid trillions of financial losses.","PeriodicalId":405296,"journal":{"name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132618705","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}
Zhi Xu, Shuncheng Liu, Ziniu Wu, Xu Chen, Kai Zeng, K. Zheng, Han Su
The largest portion of urban congestion is caused by 'phantom' traffic jams, causing significant delay travel time, fuel waste, and air pollution. It frequently occurs in high-density traffics without any obvious signs of accidents or roadworks. The root cause of 'phantom' traffic jams in one-lane traffics is the sudden change in velocity of some vehicles (i.e. harsh driving behavior (HDB)), which may generate a chain reaction with accumulated impact throughout the vehicles along the lane. This paper makes the first attempt to address this notorious problem in a one-lane traffic environment through velocity control of autonomous vehicles. Specifically, we propose a velocity control framework, called PATROL (sPAtial-temporal ReinfOrcement Learning). First, we design a spatial-temporal graph inside the reinforcement learning model to process and extract the information (e.g. velocity and distance difference) of multiple vehicles ahead across several historical time steps in the interactive environment. Then, we propose an attention mechanism to characterize the vehicle interactions and an LSTM structure to understand the vehicles' driving patterns through time. At last, we modify the reward function used in previous velocity control works to enable the autonomous driving agent to predict the HDB of preceding vehicles and smoothly adjust its velocity, which could alleviate the chain reaction caused by HDB. We conduct extensive experiments to demonstrate the effectiveness and superiority of PATROL in alleviating the 'phantom' traffic jam in simulation environments. Further, on the real-world velocity control dataset, our method significantly outperforms the existing methods in terms of driving safety, comfortability, and efficiency.
{"title":"PATROL: A Velocity Control Framework for Autonomous Vehicle via Spatial-Temporal Reinforcement Learning","authors":"Zhi Xu, Shuncheng Liu, Ziniu Wu, Xu Chen, Kai Zeng, K. Zheng, Han Su","doi":"10.1145/3459637.3482283","DOIUrl":"https://doi.org/10.1145/3459637.3482283","url":null,"abstract":"The largest portion of urban congestion is caused by 'phantom' traffic jams, causing significant delay travel time, fuel waste, and air pollution. It frequently occurs in high-density traffics without any obvious signs of accidents or roadworks. The root cause of 'phantom' traffic jams in one-lane traffics is the sudden change in velocity of some vehicles (i.e. harsh driving behavior (HDB)), which may generate a chain reaction with accumulated impact throughout the vehicles along the lane. This paper makes the first attempt to address this notorious problem in a one-lane traffic environment through velocity control of autonomous vehicles. Specifically, we propose a velocity control framework, called PATROL (sPAtial-temporal ReinfOrcement Learning). First, we design a spatial-temporal graph inside the reinforcement learning model to process and extract the information (e.g. velocity and distance difference) of multiple vehicles ahead across several historical time steps in the interactive environment. Then, we propose an attention mechanism to characterize the vehicle interactions and an LSTM structure to understand the vehicles' driving patterns through time. At last, we modify the reward function used in previous velocity control works to enable the autonomous driving agent to predict the HDB of preceding vehicles and smoothly adjust its velocity, which could alleviate the chain reaction caused by HDB. We conduct extensive experiments to demonstrate the effectiveness and superiority of PATROL in alleviating the 'phantom' traffic jam in simulation environments. Further, on the real-world velocity control dataset, our method significantly outperforms the existing methods in terms of driving safety, comfortability, and efficiency.","PeriodicalId":405296,"journal":{"name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","volume":"338 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133084416","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：