ECIR 2016 Paper Modelling User Interest for Zero-query Ranking
来源:互联网 发布:virtualbox怎么用软件 编辑:程序博客网 时间:2024/05/17 07:09
中文简介:本文对智能个人助理(如Google Now,Microsoft Cortana)中的信息卡片排序进行了研究,从user modeling的角度提出了三组排序特征:implicit feedback features, entity based user interests features以及user demographic features. 其中entity features的提取用到了word embedding和knowledge base信息进行语义相似度的计算。基于大规模产品日志数据的实验表明,提出的排序特征可以提升信息卡片的检索质量。
论文出处:ECIR'16.
英文摘要: Proactive search systems like Google Now and Microsoft Cortana have gained increasing popularity with the growth of mobile Internet. Unlike traditional reactive search systems where search engines return results in response to queries issued by the users, proactive systems actively push information cards to the users on mobile devices based on the context around time, location, environment (e.g., weather), and user interests. A proactive system is a zero-query in-formation retrieval system, which makes user modeling critical for understanding user information needs. In this paper, we study user modeling in proactive search systems and propose a learning to rank method for proactive ranking. We explore a variety of ways of modeling user interests, ranging from direct modeling of historical interaction with content types to finer-grained entity-level modeling, and user demographical information. To reduce the feature sparsity problem in entity modeling, we propose semantic similarity features using word embedding and an entity taxonomy in knowledge base. Experiments performed with data from a large commercial proactive search system show that our method significantly outperforms a strong baseline method deployed in the production system.
下载链接:https://www.microsoft.com/en-us/research/wp-content/uploads/2016/04/ECIR16-ProactiveRanking-cameraready01042016.pdf
- ECIR 2016 Paper Modelling User Interest for Zero-query Ranking
- ECIR 2016 Paper Beyond Factoid QA: Effective Methods for Non-factoid Answer Sentence Retrieval
- 看topic modelling paper 要分成两类看
- #Paper Reading# Joint Matrix Factorization and Manifold-Ranking for Topic-Focused Multi-Document Sum
- 开通博客--for interest
- 1.Lost in Binarization: Query-Adaptive Ranking for Similar Image Search with Compact Codes笔记
- query user
- Spatial Data Modelling for 3D GIS
- Magical Data Modelling Framework for JSON
- A convolutional Neural Network for Modelling Sentences
- MEMORY-AUGMENTED ATTENTION MODELLING FOR VIDEOS
- Multimodal Memory Modelling for Video Captioning
- User Interest Profiling from User Generated Visual Content----论文笔记
- New Red Paper Available on Crafting a Great User Experience for PeopleSoft
- #One paper per week# Inferring Correspondences from Multiple Sources for Microblog User Tags
- [翻译][Paper][WWW'10]Classification-Enhanced Ranking
- [翻译][Paper][WWW'10]Classification-Enhanced Ranking (2)
- #Paper Reading# Manifold-Ranking Based Topic-Focused Multi-Document Summarization
- 给Eclipse添加各类插件
- 687D: Dividing Kingdom II
- 687E: TOF
- Detach Volume 操作 - 每天5分钟玩转 OpenStack(55)
- ECIR 2016 Paper Beyond Factoid QA: Effective Methods for Non-factoid Answer Sentence Retrieval
- ECIR 2016 Paper Modelling User Interest for Zero-query Ranking
- ICDM 2014 Paper ShellMiner Mining Organizational Phrases in Argumentative Texts in Social Media
- 《35岁高中生》
- Redis学习笔记(2)-Redis数据类型
- 基于Dubbo的分布式系统架构-使用Dubbo进行规模服务化前的工程结构优化
- smarty原则及优点
- HDU2022 海选女主角
- 我的Unity学习之路
- smarty操作