Filters








11,589 Hits in 5.5 sec

Short text categorization exploiting contextual enrichment and external knowledge

Stefano Mizzaro, Marco Pavan, Ivan Scagnetto, Martino Valenti
2014 Proceedings of the first international workshop on Social media retrieval and analysis - SoMeRA '14  
The problem • Short texts are growing • (at least) 2 reasons • Twitter 140 limit • Mobile devices, input limitations • Categorization of short texts, or #ShortTxtCateg 5 #ShortTxtCateg:  ...  • #eval • @home 13 Our approach • Exploiting Wikipedia • Search engine • Article/category labels • Category relationships • EnrichmentExploiting search engines • Time aware • We  ... 
doi:10.1145/2632188.2632205 dblp:conf/sigir/MizzaroPSV14 fatcat:wpcszowqorbezmbqeur4dnxuey

Exploiting News to Categorize Tweets: Quantifying the Impact of Different News Collections

Marco Pavan, Stefano Mizzaro, Matteo Bernardon, Ivan Scagnetto
2016 European Conference on Information Retrieval  
Short texts, due to their nature which makes them full of abbreviations and new coined acronyms, are not easy to classify. Text enrichment is emerging in the literature as a potentially useful tool.  ...  This paper is a part of a longer term research that aims at understanding the effectiveness of tweet enrichment by means of news, instead of the whole web as a knowledge source.  ...  Wikipedia category tree as external knowledge base.  ... 
dblp:conf/ecir/PavanMBS16 fatcat:flygl2pnlvbldbkumfolheat7u

Short Text Feature Enrichment Using Link Analysis on Topic-Keyword Graph [chapter]

Peng Wang, Heng Zhang, Bo Xu, Chenglin Liu, Hongwei Hao
2014 Communications in Computer and Information Science  
In this paper, we propose a novel feature enrichment method for short text classification based on the link analysis on topic-keyword graph.  ...  At last, the short text is expanded by appending these related keywords for classification. Experimental results on two open datasets validate the effectiveness of the proposed method.  ...  [5] proposed a graph-based text similarity measurement and exploited background knowledge from Wikipedia to find semantic affinity between documents. Phan et al.  ... 
doi:10.1007/978-3-662-45924-9_8 fatcat:hpbkigwc7vbvhgmutihkjhr7nq

Clustering of semantically enriched short texts

Marek Kozlowski, Henryk Rybinski
2018 Journal of Intelligent Information Systems  
We present two approaches, one based on neural-based distributional models, and the other based on external knowledge resources. The approaches are tested on SnSRC and other knowledge-poor algorithms.  ...  In addition, we test the possibilities of improving the quality of clustering ultra-short texts by means of enriching them semantically.  ...  reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.  ... 
doi:10.1007/s10844-018-0541-4 fatcat:eipabygtdrdr3ji7wqth6vic4a

Wiki3C

Peng Jiang, Huiman Hou, Lijiang Chen, Shimin Chen, Conglei Yao, Chengkai Li, Min Wang
2013 Proceedings of the sixth ACM international conference on Web search and data mining - WSDM '13  
In this paper, we exploit Wikipedia for a new task of text mining: Context-aware Concept Categorization. In the task, we focus on categorizing concepts according to their context.  ...  We exploit article link feature and category structure in Wikipedia, followed by introducing Wiki3C, an unsupervised and domain independent concept categorization approach based on context.  ...  Gabrilovich and Markovitch [2] enrich document representation through Wikipedia to improve the performance of text categorization.  ... 
doi:10.1145/2433396.2433441 dblp:conf/wsdm/JiangHCCYLW13 fatcat:ma2y3c5ebzbzlfeqb5lhgjkqoq

Leveraging Knowledge-Based Features With Multilevel Attention Mechanisms for Short Arabic Text Classification

Iyad Alagha
2022 IEEE Access  
When it comes to the Arabic language, the exploitation of external knowledge to support the classification of Arabic short text has not been widely explored.  ...  A common solution is to enrich the short text with additional semantic features extracted from external knowledge, such as Wikipedia, to help the classifier better decide on the correct class.  ...  However, when it comes to the Arabic language, little work has been done to exploit external knowledge bases to support the classification of Arabic short text.  ... 
doi:10.1109/access.2022.3175306 fatcat:jwn327xofzdyjpdcmrgo6mjyhy

A New Approach to Information Extraction in User-Centric E-Recruitment Systems

Malik Nabeel Ahmed Awan, Sharifullah Khan, Khalid Latif, Asad Masood Khattak
2019 Applied Sciences  
Furthermore, job context information is expanded using a job description domain ontology based on the contextual and knowledge information.  ...  The extracted information entities are enriched with knowledge using Linked Open Data.  ...  existing data by adding more knowledge from external sources.  ... 
doi:10.3390/app9142852 fatcat:sy62dzuvcra7zfi44xm64ytwom

Toward a Deep Neural Approach for Knowledge-Based IR [article]

Gia-Hung Nguyen, Lynda Tamine, Laure Soulier, Nathalie Bricon-Souf
2016 arXiv   pre-print
This latter issue is tackled by recent works dealing with deep representation learn ing of texts.  ...  In this context, knowledge bases (KBs) have already been acknowledged as valuable means since they allow the representation of explicit relations between entities.  ...  This model extends the objective function of the skip-gram model [10] with two regularization functions based on relational and categorical knowledge from the external resource, respectively.  ... 
arXiv:1606.07211v1 fatcat:jdypcyno3zcwphnoclk44dsfxi

Exploiting Background Knowledge for Argumentative Relation Classification

Jonathan Kobbe, Juri Opitz, Maria Becker, Ioana Hulpus, Heiner Stuckenschmidt, Anette Frank, Michael Wagner
2019 International Conference on Language, Data, and Knowledge  
We propose an argumentative relation classification system that employs linguistic as well as knowledge-based features, and investigate the effects of injecting background knowledge into a neural baseline  ...  This paper explores the difficulties and the potential effectiveness of knowledge-enhanced argument analysis, with the aim of advancing the state-of-the-art in argument analysis towards a deeper, knowledge-based  ...  This corpus consists of 112 short argumentative texts [19] . The corpus was created in German and has been translated to English. We use only the English version.  ... 
doi:10.4230/oasics.ldk.2019.8 dblp:conf/ldk/KobbeOBHSF19 fatcat:etbraev7lfavnjc7wflkselgsi

Towards Enriching DBpedia from Vertical Enumerative Structures Using a Distant Learning Approach [chapter]

Mouna Kamel, Cassia Trojahn
2018 Lecture Notes in Computer Science  
The remain semistructured textual structures, such as vertical enumerative structures (those using typographic and dispositional layout) have been however under-exploited.  ...  Our relation extraction approach achieves an overall precision of 62%, and 99% of the extracted relations can enrich DBpedia, with respect to a reference corpus.  ...  They are however under-exploited by knowledge approaches aiming at enriching semantic resources.  ... 
doi:10.1007/978-3-030-03667-6_12 fatcat:e7uv32y2sngvjj2wn4z6wcudve

Term Categorization Using Latent Semantic Analysis for Intelligent Query Processing

2019 VOLUME-8 ISSUE-10, AUGUST 2019, REGULAR ISSUE  
The objective is to retrieve only relevant documents by categorizing the short texts. In the proposed method, terms are categorized by means of Latent Semantic Analysis (LSA).  ...  Understanding and categorizing these texts for effective query processing is considered as one of the vital defy in the field of Natural Language Processing.  ...  The major challenging task is to understand and categorize these short texts.  ... 
doi:10.35940/ijitee.a1065.1191s19 fatcat:2lnqh6nwtfhzbn6z4gbfvxwu24

Incorporating External Knowledge into Machine Reading for Generative Question Answering

Bin Bi, Chen Wu, Ming Yan, Wei Wang, Jiangnan Xia, Chenliang Li
2019 Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)  
This allows the model to exploit external knowledge that is not explicitly stated in the given text, but that is relevant for generating an answer.  ...  In this paper, we propose a new neural model, Knowledge-Enriched Answer Generator (KEAG), which is able to compose a natural answer by exploiting and aggregating evidence from all four information sources  ...  the contextual passage and external knowledge.  ... 
doi:10.18653/v1/d19-1255 dblp:conf/emnlp/BiWYWXL19 fatcat:styjmolrzjbyhccarp36naqwvm

Incorporating External Knowledge into Machine Reading for Generative Question Answering [article]

Bin Bi, Chen Wu, Ming Yan, Wei Wang, Jiangnan Xia, Chenliang Li
2019 arXiv   pre-print
This allows the model to exploit external knowledge that is not explicitly stated in the given text, but that is relevant for generating an answer.  ...  In this paper, we propose a new neural model, Knowledge-Enriched Answer Generator (KEAG), which is able to compose a natural answer by exploiting and aggregating evidence from all four information sources  ...  the contextual passage and external knowledge.  ... 
arXiv:1909.02745v1 fatcat:kae4hidiejfm7fbstcv45mz4um

Query Extension with Improved User Profiles for User tailored Search taking Advantage over Folksonomy Data

Mohammed Zubair Ali Khan
2018 International Journal for Research in Applied Science and Engineering Technology  
user profiles with the assistance of associate external corpus for customized question growth.  ...  Query expansion has been widely adopted in web search as the simplest way of endeavour the anomaly of queries. customized search utilizing folksonomy knowledge has incontestible associate extreme vocabulary  ...  organize their on-line bookmarks with freely chosen short text descriptors.  ... 
doi:10.22214/ijraset.2018.6110 fatcat:nxvd2uqm7vgdtggmjqmuoxl37e

Context-aware Image Tweet Modelling and Recommendation

Tao Chen, Xiangnan He, Min-Yen Kan
2016 Proceedings of the 2016 ACM on Multimedia Conference - MM '16  
We start with tweet's intrinsic contexts, namely, 1) text within the image itself and 2) its accompanying text; and then we turn to the extrinsic contexts: 3) the external web page linked to by the tweet's  ...  To bridge this gap, we move from the images' pixels to their context and propose a context-aware image tweet modelling (CITING) framework to mine and fuse contextual text to model such social media images  ...  We also would like to thank Yongfeng Zhang and Hanwang Zhang for their help and discussions.  ... 
doi:10.1145/2964284.2964291 dblp:conf/mm/ChenHK16 fatcat:nepnjdu5vbffbhrhkisac5p5fe
« Previous Showing results 1 — 15 out of 11,589 results