Filters








2,648 Hits in 4.6 sec

Automatically Deriving Event Ontologies for a CommonSense Knowledge Base

James Allen, Will De Beaumont, Lucian Galescu, Jansen Orfan, Mary Swift, Choh Teng
unpublished
We show that we can use this system to automatically create a mid-level ontology for WordNet verbs that has good agreement with human intuition with respect to both the hypernym and causality relations  ...  The end result is a knowledge base allowing complex concepts to be reasoned about using OWL-DL reasoners.  ...  This motivates work in building a commonsense knowledge base automatically from reading online sources.  ... 
fatcat:zyadx4dajjgxnjhnyflsby4p3e

How Intelligent Are Ambient Intelligence Systems?

María J. Santofimia, Francisco Moya, Félix J. Villanueva, David Villa, Juan C. López
2010 International Journal of Ambient Computing and Intelligence (IJACI)  
This work advocates for the integration of the commonsense reasoning and understanding capabilities as the key elements in bridging the gap between idiot savant systems and real Ambient Intelligence systems  ...  the Ambient Intelligence paradigm, as an evolution of the Ubiquitous Computing, great deal of the research efforts in this field have been mainly aimed at anticipating user actions and needs, out of a  ...  Automating commonsense reasoning is a task that requires an expressive enough language, a knowledge base where to store such a large amount of knowledge, and a set of mechanisms capable of manipulating  ... 
doi:10.4018/jaci.2010010106 fatcat:b2h6u6uvnrazljdoha2zifhuvi

Modelling Functional Behavior of Event-based Systems: A Practical Knowledge-based Approach

Fahim T. Imam, Thomas R. Dean
2016 Procedia Computer Science  
In this paper, we present a practical, knowledge-based approach to model the functional behavior that incorporates the notions of Commonsense Reasoning and Functional Reasoning over its core defining aspects  ...  The main motivation behind this work was to develop a rigorous, logic-based approach to verify the levels of functional consistencies between cross-platform event-based systems.  ...  In this paper, we present a practical, knowledge-based approach of functional behavior modeling that utilizes a rigorous, ontological representation of event-based systems.  ... 
doi:10.1016/j.procs.2016.08.243 fatcat:ees5g5jhrrbuzhhvi4mevqvt5a

Dimensions of Commonsense Knowledge [article]

Filip Ilievski, Alessandro Oltramari, Kaixin Ma, Bin Zhang, Deborah L. McGuinness, Pedro Szekely
2021 arXiv   pre-print
We aim to organize these sources around a common set of dimensions of commonsense knowledge. We survey a wide range of popular commonsense sources with a special focus on their relations.  ...  Commonsense knowledge is essential for many AI applications, including those in natural language processing, visual processing, and planning.  ...  Its base events are collected from a variety of corpora, while the data for the events is collected by crowdsourcing.  ... 
arXiv:2101.04640v2 fatcat:ehkp23l2cfelrm6urgmyiyyix4

How Commonsense Knowledge Helps with Natural Language Tasks: A Survey of Recent Resources and Methodologies [article]

Yubo Xie, Pearl Pu
2021 arXiv   pre-print
natural language problems that take advantage of external knowledge bases.  ...  We first review some popular commonsense knowledge bases and commonsense reasoning benchmarks, but give more emphasis on the methodologies, including recent approaches that aim at solving some general  ...  at automatically proposing new entities and relations for an existing knowledge base [Bosselut et al., 2019] .  ... 
arXiv:2108.04674v1 fatcat:feap4jp4mrhbdfhldylzltpota

A Methodology based on Commonsense Knowledge and Ontologies for the Automatic Classification of Legal Cases

Nicola Capuano, Carmen De Maio, Saverio Salerno, Daniele Toti
2014 Proceedings of the 4th International Conference on Web Intelligence, Mining and Semantics (WIMS14) - WIMS '14  
We describe a methodology for the automatic classification of legal cases expressed in natural language, which relies on existing legal ontologies and a commonsense knowledge base.  ...  This methodology is founded on a process consisting of three phases: an enrichment of a given legal ontology by associating its terms with topics retrieved from the Wikipedia knowledge base; an extraction  ...  As a matter of fact, several ontologies have been defined for a wide range of knowledge domains (e.g.  ... 
doi:10.1145/2611040.2611048 dblp:conf/wims/CapuanoMST14 fatcat:zippuc6w7zco5o4xxgg2ftsnne

Lexical Mediation for Ontology-Based Annotation of Multimedia [chapter]

Mario Cataldi, Rossana Damiano, Vincenzo Lombardo, Antonio Pizzo
2012 New Trends of Research in Ontologies and Lexical Resources  
Such ontologies, however, are often light scale domain oriented knowledge bases, whereas the employment of wide, commonsense ontologies would improve interoperability and knowledge sharing, with beneficial  ...  commonsense ontologies.  ...  For this, we designed and implemented a tool that helps the user access the commonsense knowledge through a linguistic-based disambiguation process.  ... 
doi:10.1007/978-3-642-31782-8_7 dblp:series/tanlp/CataldiDLP13 fatcat:ospnwo57nbh2dkcak3sh4wqnna

Is your data 6-star?

Cássia Trojahn
2020 International Semantic Web Conference  
Such distinctions are however essential for many applications consuming the data, and have been since many years the subject of study in foundational ontologies.  ...  It proposes to extend the well-known 5-star rating schema to a 6-star schema, with data getting a 6-star rating when equipped with foundational distinctions.  ...  across knowledge bases.  ... 
dblp:conf/semweb/Trojahn20 fatcat:w3qo2dpotfeexcrmbb3wzeiome

EMOCause: An Easy-adaptable Approach to Extract Emotion Cause Contexts

Irene Russo, Tommaso Caselli, Francesco Rubino, Ester Boldrini, Patricio Martínez-Barco
2011 Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis  
In this paper we present a method to automatically identify linguistic contexts which contain possible causes of emotions or emotional states from Italian newspaper articles (La Repubblica Corpus).  ...  Our methodology is based on the interplay between relevant linguistic patterns and an incremental repository of common sense knowledge on emotional states and emotion eliciting situations.  ...  commonsense knowledge about events which elicit emotions or emotional states.  ... 
dblp:conf/wassa/RussoCRBM11 fatcat:gylxj6nfwzfgdfviy4hxmq576q

WordNet Hierarchy Axiomatization and the Mass-Count Distinction

Jonathan Gordon, Lenhart K. Schubert
2013 2013 IEEE Seventh International Conference on Semantic Computing  
However, it has not yet been formalized for use in a general reasoning system. In this paper, we present such a formalization.  ...  We use a semi-automatic annotation of WordNet with lexical features -most notably the mass-count distinction -to recognize inferentially different relations between concepts.  ...  I We are interested in the creation of large knowledge bases to support language understanding and commonsense problemsolving.  ... 
doi:10.1109/icsc.2013.31 dblp:conf/semco/GordonS13 fatcat:i2byjrfqfzabzk3qtuejeba5ti

Representing Context in FrameNet: A Multidimensional, Multimodal Approach

Tiago Timponi Torrent, Ely Edison da Silva Matos, Frederico Belcavello, Marcelo Viridiano, Maucha Andrade Gamonal, Alexandre Diniz da Costa, Mateus Coutinho Marim
2022 Frontiers in Psychology  
We claim that such an enriched model is capable of addressing other types of contextual information in a framenet, namely sentence-level cotext and commonsense knowledge.  ...  lexical units in sentences and (ii) a methodology for domain adaptation in Neural Machine Translation that leverages frames and qualia for representing sentence-level context.  ...  Authors also thank GNT TV Channel for granting authorization for research use and access to the episodes in the first season of the TV Travel series Pedro pelo Mundo.  ... 
doi:10.3389/fpsyg.2022.838441 pmid:35444591 pmcid:PMC9014903 fatcat:az5q6pfxlrdvxppeajblh62k3i

An ASP-based Approach to Answering Natural Language Questions for Texts [article]

Dhruva Pendharkar, Kinjal Basu, Farhad Shakerin, Gopal Gupta
2021 arXiv   pre-print
An approach based on answer set programming (ASP) is proposed in this paper for representing knowledge generated from natural language texts.  ...  Knowledge in a text is modeled using a Neo Davidsonian-like formalism, which is then represented as an answer set program.  ...  In Cyc, knowledge is presented in the form of a vast collection of ontologies that consist of implicit knowledge and rules about the world that represents commonsense knowledge.  ... 
arXiv:2112.11241v1 fatcat:wl7upalae5cjvibd4epxvoyw5u

ConceptNet — A Practical Commonsense Reasoning Tool-Kit

H Liu, P Singh
2004 BT technology journal  
The knowledge base is a semantic network presently consisting of over 1.6 million assertions of commonsense knowledge encompassing the spatial, physical, social, temporal, and psychological aspects of  ...  ConceptNet is a freely available commonsense knowledge base and natural-language-processing tool-kit which supports many practical textual-reasoning tasks over real-world documents including topic-gisting  ...  Finally, we thank the blind reviewers for their thoughtful feedback.  ... 
doi:10.1023/b:bttj.0000047600.45421.6d fatcat:hokobaz4xbfuba2fabzm7uirfy

Knowledge Acquisition from EPC Models for Extraction of Process Patterns in Engineering Domains

Andreas Bögl, Maximilian Kobler, Michael Schrefl
2008 Multikonferenz Wirtschaftsinformatik  
This paper presents an approach for the automated extraction of process patterns from Event-driven Process Chain (EPC) models in engineering domains.  ...  Semantic patterns are employed to analyze the lexical structure of these terms and to relate them to instances of a reference ontology.  ...  Acknowledgements We would like to thank Siemens CT SE3 for providing EPC models in engineering domains.  ... 
dblp:conf/mkwi/BoglKS08 fatcat:z4kiprvstbhppeedbccvi2ayoi

Commonsense Knowledge Reasoning and Generation with Pre-trained Language Models: A Survey [article]

Prajjwal Bhargava, Vincent Ng
2022 arXiv   pre-print
While commonsense knowledge acquisition and reasoning has traditionally been a core research topic in the knowledge representation and reasoning community, recent years have seen a surge of interest in  ...  This paper presents a survey of these tasks, discusses the strengths and weaknesses of state-of-the-art pre-trained models for commonsense reasoning and generation as revealed by these tasks, and reflects  ...  For instance, there have been notable attempts to manually create large-scale commonsense knowledge bases (e.g., Cyc (Lenat 1995) and automatically acquire commonsense knowledge from the Web (e.g., Open  ... 
arXiv:2201.12438v1 fatcat:tpqwhagvnvdzlhzmbm6ajhokcm
« Previous Showing results 1 — 15 out of 2,648 results