Filters








59,959 Hits in 3.5 sec

Topic Difficulty Prediction in Entity Ranking [chapter]

Anne-Marie Vercoustre, Jovan Pehcevski, Vladimir Naumovski
2009 Lecture Notes in Computer Science  
In this paper, we show that the knowledge of predicted classes of topic difficulty can be used to further improve the entity ranking performance.  ...  Our experiments suggest that topic difficulty prediction is a promising approach that could be exploited to improve the effectiveness of entity ranking.  ...  Acknowledgements Most of this work was completed while Vladimir Naumovski was doing his internship at INRIA in 2008.  ... 
doi:10.1007/978-3-642-03761-0_29 fatcat:qggfph7cmzdidoxssqxql7sg6m

Estimating query difficulty for news prediction retrieval

Nattiya Kanhabua, Kjetil Nørvåg
2012 Proceedings of the 21st ACM international conference on Information and knowledge management - CIKM '12  
In this paper, we study how to determine the difficulty in retrieving predictions for a given news story.  ...  More precisely, we address the query difficulty estimation problem for news prediction retrieval.  ...  Thus, we take into account prediction robustness by employing several ranking models (cf. Section 4) in determining the difficulty of a given query or topic.  ... 
doi:10.1145/2396761.2398707 dblp:conf/cikm/KanhabuaN12a fatcat:63mf66ejinafzkmpqmoxapfpui

Predicting the effectiveness of keyword queries on databases

Shiwen Cheng, Arash Termehchy, Vagelis Hristidis
2012 Proceedings of the 21st ACM international conference on Information and knowledge management - CIKM '12  
Keyword query interfaces (KQIs) for databases provide easy access to data, but often suffer from low ranking quality, i.e. low precision and/or recall, as shown in recent benchmarks.  ...  We evaluate our query difficulty prediction model against two relevance judgment benchmarks for keyword search on databases, INEX and SemSearch.  ...  They compare the probability distribution of topics in the top ranked documents with the probability distribution of topics of the whole collection to predict the degree of the difficulty of the query.  ... 
doi:10.1145/2396761.2398422 dblp:conf/cikm/ChengTH12 fatcat:mqya5hogvfexlcm5nmcaaqrrze

Efficient Prediction of Difficult Keyword Queries over Databases

Shiwen Cheng, Arash Termehchy, V. Hristidis
2014 IEEE Transactions on Knowledge and Data Engineering  
We evaluate our query difficulty prediction model against two effectiveness benchmarks for popular keyword search ranking methods.  ...  Keyword queries on databases provide easy access to data, but often suffer from low ranking quality, i.e., low precision and/or recall, as shown in recent benchmarks.  ...  They compare the probability distribution of topics in the top ranked documents with the probability distribution of topics of the whole collection to predict the degree of the difficulty of the query.  ... 
doi:10.1109/tkde.2013.140 fatcat:psn3jdopkzewrb2xao2grpt7fi

Novel Approach for Predicting Difficult Keyword Queries over Databases using Effective Ranking

G. Ramakrishnan, S. Uma Maheswari
2015 International Journal of Engineering Research and  
In the existing work, analyses the characteristics of hard queries and propose a novel framework to measure the degree of difficulty for a keyword query in excess of a database, considering both the structure  ...  In order to overcome these drawbacks, we are proposing the improved ranking algorithm which is used to enhance the accuracy rate of the system.  ...  Our proposed query difficulty prediction model falls in this category Some methods use machine learning techniques to learn the properties of difficult queries and predict their hardness.  ... 
doi:10.17577/ijertv4is030251 fatcat:jmm6kuoyuzeoliphug2xf2pahu

Characterizing web content, user interests, and search behavior by reading level and topic

Jin Young Kim, Kevyn Collins-Thompson, Paul N. Bennett, Susan T. Dumais
2012 Proceedings of the fifth ACM international conference on Web search and data mining - WSDM '12  
entities in Web searchusers, websites, and queries.  ...  To help improve our modeling and understanding of this diversity, we apply automatic text classifiers, based on reading difficulty and topic prediction, to estimate a novel type of profile for important  ...  the topics or range of difficulty levels they cover.  ... 
doi:10.1145/2124295.2124323 dblp:conf/wsdm/KimCBD12 fatcat:bzp4wlh5mrhjhp3lv6gjf6zb2y

Improved Neural Relation Detection for Knowledge Base Question Answering [article]

Mo Yu, Wenpeng Yin, Kazi Saidul Hasan, Cicero dos Santos, Bing Xiang, Bowen Zhou
2017 arXiv   pre-print
In this paper, we propose a hierarchical recurrent neural network enhanced by residual learning that detects KB relations given an input question.  ...  Additionally, we propose a simple KBQA system that integrates entity linking and our proposed relation detector to enable one enhance another.  ...  Sections 5.1 and 5.2 elaborate how our relation detection help to re-rank entities in the initial entity linking, and then those re-ranked entities enable more accurate relation detection.  ... 
arXiv:1704.06194v2 fatcat:uzenppnb2rd45c5mzbre2d5yx4

Capturing Global Informativeness in Open Domain Keyphrase Extraction [article]

Si Sun, Zhenghao Liu, Chenyan Xiong, Zhiyuan Liu, Jie Bao
2021 arXiv   pre-print
Further analyses reveal the significant advantages of JointKPE in predicting long and non-entity keyphrases, which are challenging for previous neural KPE methods.  ...  JointKPE learns to rank keyphrases by estimating their informativeness in the entire document and is jointly trained on the keyphrase chunking task to guarantee the phraseness of keyphrase candidates.  ...  Despite the challenge, JointKPE and its informative ranking version (Rank) significantly outperform other methods in predicting non-entity keyphrases.  ... 
arXiv:2004.13639v2 fatcat:zx53kxez7rdyxo4rq353iakdgm

Improved Neural Relation Detection for Knowledge Base Question Answering

Mo Yu, Wenpeng Yin, Kazi Saidul Hasan, Cicero dos Santos, Bing Xiang, Bowen Zhou
2017 Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)  
In this paper, we propose a hierarchical recurrent neural network enhanced by residual learning which detects KB relations given an input question.  ...  Additionally, we propose a simple KBQA system that integrates entity linking and our proposed relation detector to make the two components enhance each other.  ...  Sections 5.1 and 5.2 elaborate how our relation detection help to re-rank entities in the initial entity linking, and then those re-ranked entities enable more accurate relation detection.  ... 
doi:10.18653/v1/p17-1053 dblp:conf/acl/YuYHSXZ17 fatcat:2swegocdifegtdcbf6lqzmwqfu

Predicting event-relatedness of popular queries

Seyyedeh Newsha Ghoreishi, Aixin Sun
2013 Proceedings of the 22nd ACM international conference on Conference on information & knowledge management - CIKM '13  
Our analysis shows that the number of named entities in search results and their appearances in Wikipedia are among the most discriminative features for query event-relatedness prediction.  ...  In this paper, we identify 20 features including both contextual and temporal features from a small set of search results of a query and predict its event-relatedness.  ...  Query clarity has been used to predict query difficulty and a large KL divergence indicates a clear and unambiguous query [2] .  ... 
doi:10.1145/2505515.2507853 dblp:conf/cikm/GhoreishiS13 fatcat:agypapk3bngm7j3y3zjn725vky

Text Readability Assessment for Second Language Learners

Menglin Xia, Ekaterina Kochmar, Ted Briscoe
2016 Proceedings of the 11th Workshop on Innovative Use of NLP for Building Educational Applications  
One of the major challenges in this task is the lack of significantly sized level-annotated data.  ...  In our experiments, the best performing model for readability on learner texts achieves an accuracy of 0.797 and PCC of 0.938.  ...  Acknowledgements We thank Cambridge Assessment for their assistance in the collection of the language testing data.  ... 
doi:10.18653/v1/w16-0502 dblp:conf/bea/XiaKB16 fatcat:wok7zumrbfgwbmp2srkua4aszy

THU QUANTA at TAC 2008 QA and RTE Track

Fangtao Li, Zhicheng Zheng, Yang Tang, Fan Bu, Rong Ge, Xiaoyan Zhu, Xian Zhang, Minlie Huang
2008 Text Analysis Conference  
This paper describes the systems of THU QUANTA in Text Analysis Conference (TAC) 2008. We participated in the Question Answering (QA) track, and the Recognizing Textual Entailment (RTE) track.  ...  We detect the exact entity and relation mismatch to recognize the false entailment. The evaluation results show that the proposed approaches are very effective for the QA and RTE tasks.  ...  If the time and date mismatch, we predict it is false entailment. 3) Location Mismatch For each location entity in H, if there is no corresponding entity in T, we predict it is false entailment.  ... 
dblp:conf/tac/LiZTBGZZH08 fatcat:4jrpex3urnaflnqqpbfvv55ojm

Back to the Past

Nam Khanh Tran, Andrea Ceroni, Nattiya Kanhabua, Claudia Niederée
2015 Proceedings of the Eighth ACM International Conference on Web Search and Data Mining - WSDM '15  
For this purpose, we propose (1) different query formulation methods for retrieving contextualization candidates and (2) ranking methods taking into account topical and temporal relevance as well as complementarity  ...  In this paper, we present an approach for time-aware recontextualization, which takes those requirements into account in order to improve reading experience.  ...  Prediction Performances The query formulation method described in Section 4.3 is based on predicting the performances (recall in our case) of candidate queries, ranking them according to the prediction  ... 
doi:10.1145/2684822.2685315 dblp:conf/wsdm/TranCKN15 fatcat:os6vzcuairc3deza6d6wbhpayq

PP-Rec: News Recommendation with Personalized User Interest and Time-aware News Popularity [article]

Tao Qi, Fangzhao Wu, Chuhan Wu, Yongfeng Huang
2021 arXiv   pre-print
In general, popular news usually contain important information and can attract users with different interests. Besides, they are usually diverse in content and topic.  ...  However, these methods usually have difficulties in making accurate recommendations to cold-start users, and tend to recommend similar news with those users have read.  ...  News Ranking and Model Training In this section, we introduce how we rank the candidate news and train the model in detail.  ... 
arXiv:2106.01300v2 fatcat:cg6xzv3y4rdhzcjcclv4efgaaq

Complex Knowledge Base Question Answering: A Survey [article]

Yunshi Lan, Gaole He, Jinhao Jiang, Jing Jiang, Wayne Xin Zhao, Ji-Rong Wen
2022 arXiv   pre-print
In detail, we begin with introducing the complex KBQA task and relevant background.  ...  Therefore, in recent years, researchers propose a large number of novel methods, which looked into the challenges of answering complex questions.  ...  In the entity ranking paradigm, the entities contained in G q are candidates for answer prediction Ãq .  ... 
arXiv:2108.06688v2 fatcat:frcdrrhbsncm3kprehnz563yfq
« Previous Showing results 1 — 15 out of 59,959 results