Semantic similarity based retrieval is playing an increasingly important role in many IR systems such as modern web search, question-answering, similar document retrieval etc. Improvements in retrieval of semantically similar content are very significant to applications like Quora, Stack Overflow, Siri etc. We propose a novel unsupervised model for semantic similarity based content retrieval, where we construct semantic flow graphs for each query, and introduce the concept of "soft seeding" in graph based semi-supervised learning (SSL) to convert this into an unsupervised model. We demonstrate the effectiveness of our model on an equivalent question retrieval problem on the Stack Exchange QA dataset, where our unsupervised approach significantly outperforms the state-of-the-art unsupervised models, and produces comparable results to the best supervised models. Our research provides a method to tackle semantic similarity based retrieval without any training data, and allows seamless extension to different domain QA communities, as well as to other semantic equivalence tasks.
{"title":"Soft Seeded SSL Graphs for Unsupervised Semantic Similarity-based Retrieval","authors":"Avikalp Srivastava, Madhav Datt","doi":"10.1145/3132847.3133162","DOIUrl":"https://doi.org/10.1145/3132847.3133162","url":null,"abstract":"Semantic similarity based retrieval is playing an increasingly important role in many IR systems such as modern web search, question-answering, similar document retrieval etc. Improvements in retrieval of semantically similar content are very significant to applications like Quora, Stack Overflow, Siri etc. We propose a novel unsupervised model for semantic similarity based content retrieval, where we construct semantic flow graphs for each query, and introduce the concept of \"soft seeding\" in graph based semi-supervised learning (SSL) to convert this into an unsupervised model. We demonstrate the effectiveness of our model on an equivalent question retrieval problem on the Stack Exchange QA dataset, where our unsupervised approach significantly outperforms the state-of-the-art unsupervised models, and produces comparable results to the best supervised models. Our research provides a method to tackle semantic similarity based retrieval without any training data, and allows seamless extension to different domain QA communities, as well as to other semantic equivalence tasks.","PeriodicalId":20449,"journal":{"name":"Proceedings of the 2017 ACM on Conference on Information and Knowledge Management","volume":"224 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2017-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75811381","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}
Social recommendation has been an active research topic over the last decade, based on the assumption that social information from friendship networks is beneficial for improving recommendation accuracy, especially when dealing with cold-start users who lack sufficient past behavior information for accurate recommendation. However, it is nontrivial to use such information, since some of a person's friends may share similar preferences in certain aspects, but others may be totally irrelevant for recommendations. Thus one challenge is to explore and exploit the extend to which a user trusts his/her friends when utilizing social information to improve recommendations. On the other hand, most existing social recommendation models are non-interactive in that their algorithmic strategies are based on batch learning methodology, which learns to train the model in an offline manner from a collection of training data which are accumulated from users? historical interactions with the recommender systems. In the real world, new users may leave the systems for the reason of being recommended with boring items before enough data is collected for training a good model, which results in an inefficient customer retention. To tackle these challenges, we propose a novel method for interactive social recommendation, which not only simultaneously explores user preferences and exploits the effectiveness of personalization in an interactive way, but also adaptively learns different weights for different friends. In addition, we also give analyses on the complexity and regret of the proposed model. Extensive experiments on three real-world datasets illustrate the improvement of our proposed method against the state-of-the-art algorithms.
{"title":"Interactive Social Recommendation","authors":"Xin Wang, S. Hoi, Chenghao Liu, M. Ester","doi":"10.1145/3132847.3132880","DOIUrl":"https://doi.org/10.1145/3132847.3132880","url":null,"abstract":"Social recommendation has been an active research topic over the last decade, based on the assumption that social information from friendship networks is beneficial for improving recommendation accuracy, especially when dealing with cold-start users who lack sufficient past behavior information for accurate recommendation. However, it is nontrivial to use such information, since some of a person's friends may share similar preferences in certain aspects, but others may be totally irrelevant for recommendations. Thus one challenge is to explore and exploit the extend to which a user trusts his/her friends when utilizing social information to improve recommendations. On the other hand, most existing social recommendation models are non-interactive in that their algorithmic strategies are based on batch learning methodology, which learns to train the model in an offline manner from a collection of training data which are accumulated from users? historical interactions with the recommender systems. In the real world, new users may leave the systems for the reason of being recommended with boring items before enough data is collected for training a good model, which results in an inefficient customer retention. To tackle these challenges, we propose a novel method for interactive social recommendation, which not only simultaneously explores user preferences and exploits the effectiveness of personalization in an interactive way, but also adaptively learns different weights for different friends. In addition, we also give analyses on the complexity and regret of the proposed model. Extensive experiments on three real-world datasets illustrate the improvement of our proposed method against the state-of-the-art algorithms.","PeriodicalId":20449,"journal":{"name":"Proceedings of the 2017 ACM on Conference on Information and Knowledge Management","volume":"111 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2017-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91348920","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}
People often publish online texts to express their stances, which reflect the essential viewpoints they stand. Stance identification has been an important research topic in text analysis and facilitates many applications in business, public security and government decision making. Previous work on stance identification solely focuses on classifying the supportive or unsupportive attitude towards a certain topic/entity. The other important type of stance identification, multiple stance identification, was largely ignored in previous research. In contrast, multiple stance identification focuses on identifying different standpoints of multiple parties involved in online texts. In this paper, we address the problem of recognizing distinct standpoints implied in textual data. As people are inclined to discuss the topics favorable to their standpoints, topics thus can provide distinguishable information of different standpoints. We propose a topic-based method for standpoint identification. To acquire more distinguishable topics, we further enhance topic model by adding constraints on document-topic distributions. We finally conduct experimental studies on two real datasets to verify the effectiveness of our approach to multiple stance identification.
{"title":"An Enhanced Topic Modeling Approach to Multiple Stance Identification","authors":"Junjie Lin, W. Mao, Yuhao Zhang","doi":"10.1145/3132847.3133145","DOIUrl":"https://doi.org/10.1145/3132847.3133145","url":null,"abstract":"People often publish online texts to express their stances, which reflect the essential viewpoints they stand. Stance identification has been an important research topic in text analysis and facilitates many applications in business, public security and government decision making. Previous work on stance identification solely focuses on classifying the supportive or unsupportive attitude towards a certain topic/entity. The other important type of stance identification, multiple stance identification, was largely ignored in previous research. In contrast, multiple stance identification focuses on identifying different standpoints of multiple parties involved in online texts. In this paper, we address the problem of recognizing distinct standpoints implied in textual data. As people are inclined to discuss the topics favorable to their standpoints, topics thus can provide distinguishable information of different standpoints. We propose a topic-based method for standpoint identification. To acquire more distinguishable topics, we further enhance topic model by adding constraints on document-topic distributions. We finally conduct experimental studies on two real datasets to verify the effectiveness of our approach to multiple stance identification.","PeriodicalId":20449,"journal":{"name":"Proceedings of the 2017 ACM on Conference on Information and Knowledge Management","volume":"46 29 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2017-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78785308","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}
Many modern database-backed web applications are built upon Object Relational Mapping (ORM) frameworks. While such frame- works ease application development by abstracting persistent data as objects, such convenience comes with a performance cost. In this paper, we studied 27 real-world open-source applications built on top of the popular Ruby on Rails ORM framework, with the goal to understand the database-related performance inefficiencies in these applications. We discovered a number of inefficiencies rang- ing from physical design issues to how queries are expressed in the application code. We applied static program analysis to identify and measure how prevalent these issues are, then suggested techniques to alleviate these issues and measured the potential performance gain as a result. These techniques significantly reduce database query time (up to 91%) and the webpage response time (up to 98%). Our study provides guidance to the design of future database engines and ORM frameworks to support database application that are performant yet without sacrificing programmability.
许多现代数据库支持的web应用程序都是建立在对象关系映射(ORM)框架之上的。虽然这种框架通过将持久数据抽象为对象来简化应用程序开发，但这种便利是以性能为代价的。在本文中，我们研究了基于流行的Ruby on Rails ORM框架构建的27个真实的开源应用程序，目的是了解这些应用程序中与数据库相关的性能低下。我们发现了从物理设计问题到如何在应用程序代码中表达查询等一系列低效率问题。我们应用静态程序分析来识别和测量这些问题的普遍程度，然后建议缓解这些问题的技术，并测量潜在的性能增益。这些技术显著减少了数据库查询时间(最多91%)和网页响应时间(最多98%)。我们的研究为未来数据库引擎和ORM框架的设计提供了指导，以支持性能良好但不牺牲可编程性的数据库应用程序。
{"title":"Understanding Database Performance Inefficiencies in Real-world Web Applications","authors":"Cong Yan, Alvin Cheung, Junwen Yang, Shan Lu","doi":"10.1145/3132847.3132954","DOIUrl":"https://doi.org/10.1145/3132847.3132954","url":null,"abstract":"Many modern database-backed web applications are built upon Object Relational Mapping (ORM) frameworks. While such frame- works ease application development by abstracting persistent data as objects, such convenience comes with a performance cost. In this paper, we studied 27 real-world open-source applications built on top of the popular Ruby on Rails ORM framework, with the goal to understand the database-related performance inefficiencies in these applications. We discovered a number of inefficiencies rang- ing from physical design issues to how queries are expressed in the application code. We applied static program analysis to identify and measure how prevalent these issues are, then suggested techniques to alleviate these issues and measured the potential performance gain as a result. These techniques significantly reduce database query time (up to 91%) and the webpage response time (up to 98%). Our study provides guidance to the design of future database engines and ORM frameworks to support database application that are performant yet without sacrificing programmability.","PeriodicalId":20449,"journal":{"name":"Proceedings of the 2017 ACM on Conference on Information and Knowledge Management","volume":"84 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2017-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76799483","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}
Junxing Zhu, Jiawei Zhang, Lifang He, Quanyuan Wu, Bin Zhou, Chenwei Zhang, Philip S. Yu
Anchor links connect information entities, such as entities of movies or products, across networks from different sources, and thus information in these networks can be transferred directly via anchor links. Therefore, anchor links have great value to many cross-network applications, such as cross-network social link prediction and cross-network recommendation. In this paper, we focus on studying the recommendation problem that can provide ratings of items or services. To address the problem, we propose a Cross-network Collaborative Matrix Factorization (CCMF) recommendation framework based on broad learning setting, which can effectively integrate multi-source information and alleviate the sparse information problem in each individual network. Based on item anchor links CCMF can fuse item similarity information and item latent information across networks from different sources. And different from most of the traditional works, CCMF can make multi-source recommendation tasks collaborate together via the information transfer based on the broad learning setting. During the transfer process, a novel cross-network similarity transfer method is applied to keep the consistency of item similarities between two different networks, and a domain adaptation matrix is used to overcome the domain difference problem. We conduct experiments to compare the proposed CCMF method with both classic and state-of-the-art recommendation techniques. The experimental results illustrate that CCMF outperforms other methods in different experimental circumstances, and has great advantages on dealing with different data sparse problems.
{"title":"Broad Learning based Multi-Source Collaborative Recommendation","authors":"Junxing Zhu, Jiawei Zhang, Lifang He, Quanyuan Wu, Bin Zhou, Chenwei Zhang, Philip S. Yu","doi":"10.1145/3132847.3132976","DOIUrl":"https://doi.org/10.1145/3132847.3132976","url":null,"abstract":"Anchor links connect information entities, such as entities of movies or products, across networks from different sources, and thus information in these networks can be transferred directly via anchor links. Therefore, anchor links have great value to many cross-network applications, such as cross-network social link prediction and cross-network recommendation. In this paper, we focus on studying the recommendation problem that can provide ratings of items or services. To address the problem, we propose a Cross-network Collaborative Matrix Factorization (CCMF) recommendation framework based on broad learning setting, which can effectively integrate multi-source information and alleviate the sparse information problem in each individual network. Based on item anchor links CCMF can fuse item similarity information and item latent information across networks from different sources. And different from most of the traditional works, CCMF can make multi-source recommendation tasks collaborate together via the information transfer based on the broad learning setting. During the transfer process, a novel cross-network similarity transfer method is applied to keep the consistency of item similarities between two different networks, and a domain adaptation matrix is used to overcome the domain difference problem. We conduct experiments to compare the proposed CCMF method with both classic and state-of-the-art recommendation techniques. The experimental results illustrate that CCMF outperforms other methods in different experimental circumstances, and has great advantages on dealing with different data sparse problems.","PeriodicalId":20449,"journal":{"name":"Proceedings of the 2017 ACM on Conference on Information and Knowledge Management","volume":"57 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2017-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85643842","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}
Extracting records from web pages enables a number of important applications and has immense value due to the amount and diversity of available information that can be extracted. This problem, although vastly studied, remains open because it is not a trivial one. Due to the scale of data, a feasible approach must be both automatic and efficient (and of course effective). We present here a novel approach, fully automatic and computationally efficient, using signal processing techniques to detect regularities and patterns in the structure of web pages. Our approach segments the web page, detects the data regions within it, identifies the records boundaries and aligns the records. Results show high f-score and linearithmic time complexity behaviour.
{"title":"Extracting Records from the Web Using a Signal Processing Approach","authors":"R. P. Velloso, C. Dorneles","doi":"10.1145/3132847.3132875","DOIUrl":"https://doi.org/10.1145/3132847.3132875","url":null,"abstract":"Extracting records from web pages enables a number of important applications and has immense value due to the amount and diversity of available information that can be extracted. This problem, although vastly studied, remains open because it is not a trivial one. Due to the scale of data, a feasible approach must be both automatic and efficient (and of course effective). We present here a novel approach, fully automatic and computationally efficient, using signal processing techniques to detect regularities and patterns in the structure of web pages. Our approach segments the web page, detects the data regions within it, identifies the records boundaries and aligns the records. Results show high f-score and linearithmic time complexity behaviour.","PeriodicalId":20449,"journal":{"name":"Proceedings of the 2017 ACM on Conference on Information and Knowledge Management","volume":"45 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2017-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85967110","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}
Antonia Saravanou, I. Katakis, G. Valkanas, V. Kalogeraki, D. Gunopulos
Social networks have become the de facto online resource for people to share, comment on and be informed about events pertinent to their interests and livelihood, ranging from road traffic or an illness to concerts and earthquakes, to economics and politics. This has been the driving force behind research endeavors that analyse such data. In this paper, we focus on how Content Networks can help us identify events effectively. Content Networks incorporate both structural and content-related information of a social network in a unified way, at the same time, bringing together two disparate lines of research: graph-based and content-based event discovery in social media. We model interactions of two types of nodes, users and content, and introduce an algorithm that builds heterogeneous, dynamic graphs, in addition to revealing content links in the network's structure. By linking similar content nodes and tracking connected components over time, we can effectively identify different types of events. Our evaluation on social media streaming data suggests that our approach outperforms state-of-the-art techniques, while showcasing the significance of hidden links to the quality of the results.
{"title":"Revealing the Hidden Links in Content Networks: An Application to Event Discovery","authors":"Antonia Saravanou, I. Katakis, G. Valkanas, V. Kalogeraki, D. Gunopulos","doi":"10.1145/3132847.3133148","DOIUrl":"https://doi.org/10.1145/3132847.3133148","url":null,"abstract":"Social networks have become the de facto online resource for people to share, comment on and be informed about events pertinent to their interests and livelihood, ranging from road traffic or an illness to concerts and earthquakes, to economics and politics. This has been the driving force behind research endeavors that analyse such data. In this paper, we focus on how Content Networks can help us identify events effectively. Content Networks incorporate both structural and content-related information of a social network in a unified way, at the same time, bringing together two disparate lines of research: graph-based and content-based event discovery in social media. We model interactions of two types of nodes, users and content, and introduce an algorithm that builds heterogeneous, dynamic graphs, in addition to revealing content links in the network's structure. By linking similar content nodes and tracking connected components over time, we can effectively identify different types of events. Our evaluation on social media streaming data suggests that our approach outperforms state-of-the-art techniques, while showcasing the significance of hidden links to the quality of the results.","PeriodicalId":20449,"journal":{"name":"Proceedings of the 2017 ACM on Conference on Information and Knowledge Management","volume":"57 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2017-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84993552","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 development of large-scale knowledge bases, people are building systems which give simple answers to questions based on consolidate facts. In this paper, we focus on simple questions, which ask about only a subject and relation in the knowledge base. Observing that certain parts of a question usually overlap with names of its corresponding subject and relation in the knowledge base, we argue that a question is formed by a mixture of copying and generation. To model that, we propose a sequence-to-sequence (seq2seq) architecture which encodes a candidate subject-relation pair and decodes it into the given question, where the decoding probability is used to select the best candidate. In our decoder, the copying mode points the subject or relation and duplicates its name, while the generating mode summarizes the meaning of the subject-relation pair and produces a word to smooth the question. Realizing that although sometimes a subject or relation is pointed, different names or keywords might be used, we also incorporate a paraphrasing mode to supplement the copying mode using an automatically mined lexicon. Extensive experiments on the largest dataset exhibit our better performance compared with the state-of-the-art methods.
{"title":"Knowledge-based Question Answering by Jointly Generating, Copying and Paraphrasing","authors":"Shuguang Zhu, Xiang Cheng, Sen Su, S. Lang","doi":"10.1145/3132847.3133064","DOIUrl":"https://doi.org/10.1145/3132847.3133064","url":null,"abstract":"With the development of large-scale knowledge bases, people are building systems which give simple answers to questions based on consolidate facts. In this paper, we focus on simple questions, which ask about only a subject and relation in the knowledge base. Observing that certain parts of a question usually overlap with names of its corresponding subject and relation in the knowledge base, we argue that a question is formed by a mixture of copying and generation. To model that, we propose a sequence-to-sequence (seq2seq) architecture which encodes a candidate subject-relation pair and decodes it into the given question, where the decoding probability is used to select the best candidate. In our decoder, the copying mode points the subject or relation and duplicates its name, while the generating mode summarizes the meaning of the subject-relation pair and produces a word to smooth the question. Realizing that although sometimes a subject or relation is pointed, different names or keywords might be used, we also incorporate a paraphrasing mode to supplement the copying mode using an automatically mined lexicon. Extensive experiments on the largest dataset exhibit our better performance compared with the state-of-the-art methods.","PeriodicalId":20449,"journal":{"name":"Proceedings of the 2017 ACM on Conference on Information and Knowledge Management","volume":"23 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2017-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82542172","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}
Sergey Paramonov, Samuel Kolb, Tias Guns, L. D. Raedt
Spreadsheet data is widely used today by many different people and across industries. However, writing, maintaining and identifying good formulae for spreadsheets can be time consuming and error-prone. To address this issue we have introduced the TaCLe system (Tabular Constraint Learner). The system tackles an inverse learning problem: given a plain comma separated file, it reconstructs the spreadsheet formulae that hold in the tables. Two important considerations are the number of cells and constraints to check, and how to deal with multiple formulae for the same cell. Our system reasons over entire rows and columns and has an intuitive user interface for interacting with the learned constraints and data. It can be seen as an intelligent assistance tool for discovering formulae from data. As a result, the user obtains a spreadsheet that can automatically recompute dependent cells when updating or adding data.
{"title":"TaCLe: Learning Constraints in Tabular Data","authors":"Sergey Paramonov, Samuel Kolb, Tias Guns, L. D. Raedt","doi":"10.1145/3132847.3133193","DOIUrl":"https://doi.org/10.1145/3132847.3133193","url":null,"abstract":"Spreadsheet data is widely used today by many different people and across industries. However, writing, maintaining and identifying good formulae for spreadsheets can be time consuming and error-prone. To address this issue we have introduced the TaCLe system (Tabular Constraint Learner). The system tackles an inverse learning problem: given a plain comma separated file, it reconstructs the spreadsheet formulae that hold in the tables. Two important considerations are the number of cells and constraints to check, and how to deal with multiple formulae for the same cell. Our system reasons over entire rows and columns and has an intuitive user interface for interacting with the learned constraints and data. It can be seen as an intelligent assistance tool for discovering formulae from data. As a result, the user obtains a spreadsheet that can automatically recompute dependent cells when updating or adding data.","PeriodicalId":20449,"journal":{"name":"Proceedings of the 2017 ACM on Conference on Information and Knowledge Management","volume":"16 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2017-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88037067","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}
Deep learning has achieved great success as evidenced by many practical applications and contests. However, deep learning developed so far also has some inherent limitations. In particular, deep learning is not yet very adaptable to different related domains and cannot handle small data. In this talk, I will give an overview of how transfer learning can help alleviate these problems. In particular, I will present some recent progress on integrating deep learning and transfer learning together and show some interesting applications in sentiment analysis, image processing and urban computing.
{"title":"When Deep Learning Meets Transfer Learning","authors":"Qiang Yang","doi":"10.1145/3132847.3137175","DOIUrl":"https://doi.org/10.1145/3132847.3137175","url":null,"abstract":"Deep learning has achieved great success as evidenced by many practical applications and contests. However, deep learning developed so far also has some inherent limitations. In particular, deep learning is not yet very adaptable to different related domains and cannot handle small data. In this talk, I will give an overview of how transfer learning can help alleviate these problems. In particular, I will present some recent progress on integrating deep learning and transfer learning together and show some interesting applications in sentiment analysis, image processing and urban computing.","PeriodicalId":20449,"journal":{"name":"Proceedings of the 2017 ACM on Conference on Information and Knowledge Management","volume":"305 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2017-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91456292","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：