Filters








60,732 Hits in 5.5 sec

Learning to rank related entities in Web search

Changsung Kang, Dawei Yin, Ruiqiang Zhang, Nicolas Torzec, Jianzhang He, Yi Chang
2015 Neurocomputing  
Entity ranking is a recent paradigm that refers to retrieving and ranking related objects and entities from different structured sources in various scenarios.  ...  In this work, we present an extensive analysis of Web-scale entity ranking, based on machine learned ranking models using an ensemble of pair-wise preference models.  ...  In contrast to web search, the entity search results are grouped by categories of related entities, which complicates the ranking problem.  ... 
doi:10.1016/j.neucom.2015.04.004 fatcat:xmezq76o2fdd5efeygiixjis6i

Ranking related entities for web search queries

Changsung Kang, Srinivas Vadrevu, Ruiqiang Zhang, Roelof van Zwol, Lluis Garcia Pueyo, Nicolas Torzec, Jianzhang He, Yi Chang
2011 Proceedings of the 20th international conference companion on World wide web - WWW '11  
Entity ranking is a recent paradigm that refers to retrieving and ranking related objects and entities from different structured sources in various scenarios.  ...  In this work, we present an extensive analysis of Web-scale entity ranking, based on machine learned ranking models using an ensemble of pairwise preference models.  ...  CONCLUSIONS In this paper, we presented a system for ranking related entities in the context of the Web search.  ... 
doi:10.1145/1963192.1963227 dblp:conf/www/KangVZZPTHC11 fatcat:676nizdtufex5p5krpimjn5m3i

Improving Entity Recommendation with Search Log and Multi-Task Learning

Jizhou Huang, Wei Zhang, Yaming Sun, Haifeng Wang, Ting Liu
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
Entity recommendation, providing search users with an improved experience by assisting them in finding related entities for a given query, has become an indispensable feature of today's Web search engine  ...  Furthermore, in order to better model the semantics of queries, we learn the model in a multi-task learning setting where the query representation is shared across entity recommendation and context-aware  ...  We would like to thank the anonymous reviewers for their insightful comments.  ... 
doi:10.24963/ijcai.2018/571 dblp:conf/ijcai/HuangZSWL18 fatcat:wp6aafzj5nbvjfdkxwmusf2qhu

Probabilistic Topic Models for Learning Terminological Ontologies

Wei Wang, Payam Mamaani Barnaghi, Andrzej Bargiela
2010 IEEE Transactions on Knowledge and Data Engineering  
learning and entity ranking [19] .  ...  Learning to Rank The current link analysis based ranking algorithms in a sense are all "static ranking" algorithms: once the ranking function is derived, ordering of entities is determined and is irrelevant  ... 
doi:10.1109/tkde.2009.122 fatcat:ckvvtgj5ybg7ngwk3y7x5ysjta

Advance Entity Liking with a Knowledge Base

Mr.Darshan K
2016 International Journal Of Engineering And Computer Science  
Entity linking is the task to link entity mentions in text with their corresponding entities in a knowledge base.  ...  However, this task is challenging due to name variations and entity ambiguity. The large number of web applications generate knowledge base data which lead to major entity linking research.  ...  In this many search engines are available on web which points to search keyword to many unwanted and un-related topics while surfing to avoid of generation of unnecessary topics based on the requirement  ... 
doi:10.18535/ijecs/v5i6.38 fatcat:w3vrbp2yknhqnegc5mio35i26a

Improving Ranking Consistency for Web Search by Leveraging a Knowledge Base and Search Logs

Jyun-Yu Jiang, Jing Liu, Chin-Yew Lin, Pu-Jen Cheng
2015 Proceedings of the 24th ACM International on Conference on Information and Knowledge Management - CIKM '15  
The aim of this paper is to learn consistent rankings in search results for improving the relevance ranking in web search.  ...  In this paper, we propose a new idea called ranking consistency in web search. Relevance ranking is one of the biggest problems in creating an effective web search system.  ...  Although ranking consistency has never been discussed in relation to web search, the term ranking consistency is used in other other fields.  ... 
doi:10.1145/2806416.2806479 dblp:conf/cikm/JiangLLC15 fatcat:levblj5xujc5nkegf3cnhyerky

An Introduction to Entity Recommendation and Understanding

Hao Ma, Yan Ke
2015 Proceedings of the 24th International Conference on World Wide Web - WWW '15 Companion  
Entities and the Knowledge about the entities have become indispensable building blocks in modern search engines.  ...  The audience will learn and be able to understand some current research work as well as industry practices using computational intelligence techniques in entity recommendation and understanding.  ...  that tailor related entities to an individual search user's unique taste and preference.  ... 
doi:10.1145/2740908.2741991 dblp:conf/www/MaK15 fatcat:njaxsona6rgdtjvq7ewmzbsobe

Entity Recommendations in Web Search [chapter]

Roi Blanco, Berkant Barla Cambazoglu, Peter Mika, Nicolas Torzec
2013 Lecture Notes in Computer Science  
These signals are combined with a machine learned ranking model in order to produce a final recommendation of entities to user queries. This system is currently powering Yahoo!  ...  While some web search users know exactly what they are looking for, others are willing to explore topics related to an initial interest.  ...  Search product management team (in particular, Libby Lin), our editorial support (Alice Swanberg) and the members of the Taiwan search engineering team (Gibson Yang, Rong-En Fan, Yikai Tsai).  ... 
doi:10.1007/978-3-642-41338-4_3 fatcat:4afdux6n4nenpjpssgqqttpogu

Learning search tasks in queries and web pages via graph regularization

Ming Ji, Jun Yan, Siyu Gu, Jiawei Han, Xiaofei He, Wei Vivian Zhang, Zheng Chen
2011 Proceedings of the 34th international ACM SIGIR conference on Research and development in Information - SIGIR '11  
Problem definition  Query: Thinkpad T410 broken  Search task: the action that the user wants to perform towards the entity -We mainly work with named entity queries and related web pages -The search  ...  task is inferred from "other terms"  Target: queries with a certain category of named entities and the related web pages -Named entity category: a set of entities that are usually considered to be of  ...  Learning from multi-typed data  Click-based task similarity -A web page clicked by the user after issuing query might be useful in accomplishing the search task behind = 1 , … , ( ) = � 1, 0, Content  ... 
doi:10.1145/2009916.2009928 dblp:conf/sigir/JiYGHHZC11 fatcat:bblwa26gtvbolpjkvzcrerzii4

Learning to Explain Entity Relationships by Pairwise Ranking with Convolutional Neural Networks

Jizhou Huang, Wei Zhang, Shiqi Zhao, Shiqiang Ding, Haifeng Wang
2017 Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence  
Providing a plausible explanation for the relationship between two related entities is an important task in some applications of knowledge graphs, such as in search engines.  ...  In this paper, we propose an effective pairwise ranking model by leveraging clickthrough data of a Web search engine to address these two problems.  ...  We would like to thank the anonymous reviewers for their insightful comments.  ... 
doi:10.24963/ijcai.2017/561 dblp:conf/ijcai/HuangZZDW17 fatcat:w7disziujjc75oxhkfyce3nq6i

Ranking Entities for Web Queries Through Text and Knowledge

Michael Schuhmacher, Laura Dietz, Simone Paolo Ponzetto
2015 Proceedings of the 24th ACM International on Conference on Information and Knowledge Management - CIKM '15  
In this paper, we aim at automating this process by retrieving and ranking entities that are relevant to understand free-text web-style queries like Argentine British relations, which typically demand  ...  We use a learning-to-rank approach and study different features that use documents, entity mentions, and knowledge base entities -thus bridging document and entity retrieval.  ...  Downloads In order to encourage further research on the topic of retrieving entities for open-domain queries, we make our gold standard annotation for the Robust04 and the TREC Web (ClueWeb12) datasets  ... 
doi:10.1145/2806416.2806480 dblp:conf/cikm/SchuhmacherDP15 fatcat:b5wxcj6konggle6rxtoum2mkne

Combining Linked Data and Statistical Information Retrieval [chapter]

Ricardo Usbeck
2014 Lecture Notes in Computer Science  
The Semantic Web provides necessary procedures to augment the highly unstructured Web with suitable metadata in order to leverage search quality and user experience.  ...  In this article, we will outline an approach for creating a webscale, precise and efficient information system capable of understanding keyword, entity and natural language queries.  ...  Information Extraction from templated web-sites is mainly related to the field of wrapper induction. Early approaches to learning web wrappers were mostly supervised (e.g., [17, 10] ).  ... 
doi:10.1007/978-3-319-07443-6_58 fatcat:jukjpnhkzfeftlt4twe6g3glzu

Context-Guided Learning to Rank Entities [chapter]

Makoto P. Kato, Wiradee Imrattanatrai, Takehiro Yamamoto, Hiroaki Ohshima, Katsumi Tanaka
2020 Lecture Notes in Computer Science  
As the size of training data is typically small in this task, we propose a machine learning method referred to as context-guided learning (CGL) to overcome the over-fitting problem.  ...  Exploiting a large amount of contexts regarding relations between the labeling criteria (e.g. safety) and attributes, CGL guides learning in the correct direction by estimating a roughly appropriate weight  ...  Those tasks only expect that retrieved entities are ordered by the relatedness to given example entities, and do not expect different kinds of orders within related entities.  ... 
doi:10.1007/978-3-030-45439-5_6 fatcat:gnwngytvljf5hpmwo2fc5qhegm

The PISAB Question Answering System

Giuseppe Attardi, Cristian Burrini
2000 Text Retrieval Conference  
In the answering phase we exploit the index previously built in order to focus the search for the answer to just the most relevant documents.  ...  Knowledge extracted from documents is modeled as a set of entities extracted from text and by relations between them. During the learning phase we index documents using the entities they contain.  ...  The most relevant ones, according to the search engine rank, are further analyzed in order to extract the candidate answers.  ... 
dblp:conf/trec/AttardiB00 fatcat:mwie2jnk5jd6dagfshxntu7kkm

The first international workshop on entity-oriented search (EOS)

Krisztian Balog, Arjen P. de Vries, Pavel Serdyukov, Ji-Rong Wen
2012 SIGIR Forum  
We would also like to thank the members of the program committee for their efforts: Wo- We extend our sincere gratitude to all the authors and presenters as well as to our invited speakers for their contributions  ...  Acknowledgments We would like to thank ACM and SIGIR for hosting the workshop. We are grateful for the sponsorship received from Yandex to award the best workshop paper.  ...  [9] study the Related Entity Finding (REF) task of the TREC Entity track in their paper entitled LADS: Rapid Development of a Learning-To-Rank Based Related Entity Finding System using Open Advancement  ... 
doi:10.1145/2093346.2093353 fatcat:hqr6vdt6krbd3fgakpgz4wrhd4
« Previous Showing results 1 — 15 out of 60,732 results