Filters








27 Hits in 5.5 sec

Extracting meronyms for a biology knowledge base using distant supervision

Xiao Ling, Peter Clark, Daniel S. Weld
2013 Proceedings of the 2013 workshop on Automated knowledge base construction - AKBC '13  
This paper reports on a thorough exploration of distant supervision to learn a meronym extractor for the domain of college biology.  ...  Knowledge of objects and their parts, meronym relations, are at the heart of many question-answering systems, but manually encoding these facts is impractical.  ...  In the case of the biology domain, we were able to use distant supervision to exploit the nascent, manually-created knowledge-base.  ... 
doi:10.1145/2509558.2509560 dblp:conf/cikm/LingCW13 fatcat:256papomh5bxnbqat7snrk4l2y

Type-Aware Distantly Supervised Relation Extraction with Linked Arguments

Mitchell Koch, John Gilmer, Stephen Soderland, Daniel S. Weld
2014 Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)  
Distant supervision has become the leading method for training large-scale relation extractors, with nearly universal adoption in recent TAC knowledge-base population competitions.  ...  We find that using NEL for argument identification boosts performance over the traditional approach (named entity recognition with string match), and there is further improvement from using argument types  ...  FA8750-09-C-0181, ONR grant N00014-12-1-0211, a gift from Google, a grant from Vulcan, and the WRF / TJ Cable Professorship.  ... 
doi:10.3115/v1/d14-1203 dblp:conf/emnlp/KochGSW14 fatcat:kguk566afnd4jaelcx2aju37eu

Do Dogs have Whiskers? A New Knowledge Base of hasPart Relations [article]

Sumithra Bhakthavatsalam, Kyle Richardson, Niket Tandon, Peter Clark
2020 arXiv   pre-print
We present a new knowledge-base of hasPart relationships, extracted from a large corpus of generic statements.  ...  The knowledge base is available at https://allenai.org/data/haspartkb  ...  To complement existing resources, we have presented a new knowledge-base of hasPart relationships, constructed in a novel way by using generic sentences as a source of knowledge.  ... 
arXiv:2006.07510v1 fatcat:qym7kdtj4ngiza2mswpc6kipny

Semantic hierarchies for image annotation: A survey

Anne-Marie Tousch, Stéphane Herbin, Jean-Yves Audibert
2012 Pattern Recognition  
We analyze literature on image annotation uses and user needs, and we stress the need for automatic annotation.  ...  In this survey, we argue that using structured vocabularies is capital to the success of image annotation.  ...  Using a knowledge base, and links between objects as knowledge rules, they use inferences from parts to recognize an object.  ... 
doi:10.1016/j.patcog.2011.05.017 fatcat:hoyo5p2oyfff3lvu6yi24vbcwi

Automatically acquiring a semantic network of related concepts

Sean Szumlanski, Fernando Gomez
2010 Proceedings of the 19th ACM international conference on Information and knowledge management - CIKM '10  
I found in him a veritable Abbé Faria (in the Dumasian sense) whose breadth and depth of knowledge helped make me a more educated and wellrounded person.  ...  Relatedness between nouns is discovered automatically from lexical co-occurrence in Wikipedia texts using a novel adaptation of an information theoretic inspired measure.  ...  The network is used as a plug-in knowledge source for two graph-based WSD algorithms.  ... 
doi:10.1145/1871437.1871445 dblp:conf/cikm/SzumlanskiG10 fatcat:zhykl7wwkrfcjdigpe633odjhi

Recent advances in methods of lexical semantic relatedness – a survey

ZIQI ZHANG, ANNA LISA GENTILE, FABIO CIRAVEGNA
2012 Natural Language Engineering  
A key to this challenge rests on the technology of Information Extraction, which automatically transforms unstructured textual data into structured representation that can be interpreted and manipulated  ...  It is recognised that a fundamental task in Information Extraction is Named Entity Recognition, the goals of which are identifying references of named entities in unstructured documents, and classifying  ...  based on the pairwise semantic relatedness computed for their underlying concepts using the background knowledge extracted from a combination of multiple knowledge bases.  ... 
doi:10.1017/s1351324912000125 fatcat:b62qbqwrqfaf3gytw22yktc5ae

HyperLex: A Large-Scale Evaluation of Graded Lexical Entailment [article]

Ivan Vulić, Daniela Gerz, Douwe Kiela, Felix Hill, Anna Korhonen
2017 arXiv   pre-print
We discuss a pathway for improving semantic models to overcome this discrepancy, and indicate future application areas for improved graded LE systems.  ...  To address this, we asked hundreds of native English speakers to indicate typicality and strength of category membership between a diverse range of concept pairs on a crowdsourcing platform.  ...  A plethora of relevant work on ungraded LE do not rely on established evaluation resources, but simply extract ad-hoc LE evaluation data using distant supervision from readily available semantic resources  ... 
arXiv:1608.02117v2 fatcat:mwrgdltc5vabvdsj6hlvzw2ajm

Low-resource Learning with Knowledge Graphs: A Comprehensive Survey [article]

Jiaoyan Chen and Yuxia Geng and Zhuo Chen and Jeff Z. Pan and Yuan He and Wen Zhang and Ian Horrocks and Huajun Chen
2021 arXiv   pre-print
We next presented different applications, including not only KG augmented tasks in Computer Vision and Natural Language Processing (e.g., image classification, text classification and knowledge extraction  ...  Machine learning methods especially deep neural networks have achieved great success but many of them often rely on a number of labeled samples for training.  ...  Distant supervision for relation extraction without labeled data.  ... 
arXiv:2112.10006v3 fatcat:wkz6gjx4r5gvlhh673p3rqsmgi

HyperLex: A Large-Scale Evaluation of Graded Lexical Entailment

Ivan Vulić, Daniela Gerz, Douwe Kiela, Felix Hill, Anna Korhonen
2017 Computational Linguistics  
We discuss a pathway for improving semantic models to overcome this discrepancy, and indicate future application areas for improved graded LE systems.  ...  To address this, we asked hundreds of native English speakers to indicate typicality and strength of category membership between a diverse range of concept pairs on a crowdsourcing platform.  ...  A plethora of relevant work on ungraded LE do not rely on established evaluation resources, but simply extract ad hoc LE evaluation data using distant supervision from readily available semantic resources  ... 
doi:10.1162/coli_a_00301 fatcat:hxqbyr47cbcj3iikvb4efg2pou

Automatic generation of probabilistic relationships for improving schema matching

Laura Po, Serena Sorrentino
2011 Information Systems  
Our method is based on a probabilistic lexical annotation technique, which automatically associates one or more meanings with schema elements w.r.t. a thesaurus/lexical resource.  ...  Sorrentino, Automatic generation of probabilistic relationships for improving schema matching, Informat. Systems (2010),  ...  In [12] a method for discovering schema mappings, based on the lexical relationships extracted from WN, is proposed.  ... 
doi:10.1016/j.is.2010.09.004 fatcat:rloexir2vvczbhauj4heebqn5m

Designing Statistical Language Learners: Experiments on Noun Compounds [article]

Mark Lauer
1996 arXiv   pre-print
These results suggest that the new class of designs identified is a promising one. The experiments also serve to highlight the need for a widely applicable theory of data requirements.  ...  In pursuit of that goal, the thesis makes two main theoretical contributions: (i) it identifies a new class of designs by specifying an architecture for natural language analysis in which probabilities  ...  It uses a pattern-based method to acquire knowledge from dictionary definitions. 21 Using a set of 25 weighted analysis heuristics that use the knowledge from these definitions, a score is given to each  ... 
arXiv:cmp-lg/9609008v1 fatcat:yipwhts6ybhknmwimhbqrhchv4

Semantic Similarity from Natural Language and Ontology Analysis

Sébastien Harispe, Sylvie Ranwez, Stefan Janaqi, Jacky Montmain
2015 Synthesis Lectures on Human Language Technologies  
bases.  ...  In this context, this book focuses on semantic measures: approaches designed for comparing semantic entities such as units of language, e.g. words, sentences, or concepts and instances defined into knowledge  ...  ., 2007) , recent contributions in Knowledge Representation and Information Extraction have proved that Wikipedia can also be used to generate large knowledge bases.  ... 
doi:10.2200/s00639ed1v01y201504hlt027 fatcat:y3tbtmwwqbhydeuaf2dlqk62ui

Automated Subject Classification of Textual Documents in the Context of Web-Based Hierarchical Browsing

Koraljka Golub
2011 Knowledge organization  
Acknowledgments Many thanks to Traugott Koch for providing us with detailed comments on the manuscript, which helped improve the paper considerably.  ...  Acknowledgments The research was funded by ALVIS, an EU Sixth Framework Programme, Information Society Technologies (IST-1-002068-STP), and The Swedish Agency for Innovation Systems (P22504-1 A).  ...  FAST could also serve as a knowledge base for automated classification, like the DDC database did in Scorpion (FAST 2003) .  ... 
doi:10.5771/0943-7444-2011-3-230 fatcat:le3bszc7dzgs5if646ctxktfyi

Applications of Topic Models

Jordan Boyd-Graber, Yuening Hu, David Mimno
2017 Foundations and Trends in Information Retrieval  
Topic models like latent Dirichlet allocation (LDA) provide a framework for analyzing large datasets where observations are collected into groups.  ...  Although topic modeling has been fruitfully applied to problems social science, biology, and computer vision, it has been most widely used to model datasets where documents are modeled as exchangeable  ...  For instance, supervised topic models (Blei and McAuliffe, 2007) and relational topic models (Chang and Blei, 2009 ) use the per-document topic distribution to make predictions a document's sentiment  ... 
doi:10.1561/1500000030 fatcat:sif27skpurgsrnzjyfl2nrgrzq

Low-resource Learning with Knowledge Graphs: A Comprehensive Survey [article]

Jiaoyan Chen, Yuxia Geng, Zhuo Chen, Jeff Z. Pan, Yuan He, Wen Zhang, Ian Horrocks, Huajun Chen
2021
We next presented different applications, including not only KG augmented tasks in Computer Vision and Natural Language Processing (e.g., image classification, text classification and knowledge extraction  ...  Machine learning methods especially deep neural networks have achieved great success but many of them often rely on a number of labeled samples for training.  ...  ACKNOWLEDGMENTS This work was supported by the SIRIUS Centre for Scalable Data Access (Research Council of Norway, project 237889), eBay, Samsung Research UK, Siemens AG, and the EPSRC projects OASIS (  ... 
doi:10.48550/arxiv.2112.10006 fatcat:e2pdfnugbfad5nd4s525ge3tru
« Previous Showing results 1 — 15 out of 27 results