Filters








2,241 Hits in 5.9 sec

Refined Commonsense Knowledge from Large-Scale Web Contents [article]

Tuan-Phong Nguyen, Simon Razniewski, Julien Romero, Gerhard Weikum
2022 arXiv   pre-print
For high coverage, our method taps into the large-scale crawl C4 with broad web contents.  ...  This paper presents a method called ASCENT++ to automatically build a large-scale knowledge base (KB) of CSK assertions, with refined expressiveness and both better precision and recall than prior works  ...  CONCLUSION This paper presented ASCENT++, a methodology to extract and semantically organize advanced commonsense knowledge from large-scale web contents.  ... 
arXiv:2112.04596v2 fatcat:r45cpv4btvhmvfyntgdjwmzvc4

WebChild 2.0 : Fine-Grained Commonsense Knowledge Distillation

Niket Tandon, Gerard de Melo, Gerhard Weikum
2017 Proceedings of ACL 2017, System Demonstrations  
In this paper, we present a system based on a series of algorithms to distill fine-grained disambiguated commonsense knowledge from massive amounts of text.  ...  Our WebChild 2.0 knowledge base is one of the largest commonsense knowledge bases available, describing over 2 million disambiguated concepts and activities, connected by over 18 million assertions.  ...  Thus, they cannot automatically produce large-scale, semantically organized commonsense knowledge.  ... 
doi:10.18653/v1/p17-4020 dblp:conf/acl/TandonMW17 fatcat:vc7s4itddbfdvbkhrrshdtnlku

Inside ASCENT: Exploring a Deep Commonsense Knowledge Base and its Usage in Question Answering [article]

Tuan-Phong Nguyen, Simon Razniewski, Gerhard Weikum
2021 arXiv   pre-print
ASCENT is a fully automated methodology for extracting and consolidating commonsense assertions from web contents (Nguyen et al., WWW 2021).  ...  It advances traditional triple-based commonsense knowledge representation by capturing semantic facets like locations and purposes, and composite concepts, i.e., subgroups and related aspects of subjects  ...  Cyc (Lenat, 1995) is the first attempt to build a large-scale commonsense knowledge base.  ... 
arXiv:2105.13662v1 fatcat:pgfs4wadnzavdpl7bhozxxvari

GOOSE: A Goal-Oriented Search Engine with Commonsense [chapter]

Hugo Liu, Henry Lieberman, Ted Selker
2002 Lecture Notes in Computer Science  
For a source of common sense knowledge, we use Open Mind, a knowledge base of approximately 400,000 simple facts such as "If a pet is sick, take it to the veterinarian" garnered from a Web-wide network  ...  A novice search engine user may find searching the web for information difficult and frustrating because she may naturally express search goals rather than the topic keywords search engines need.  ...  Major search engines like Google and Yahoo have made great progress in indexing a large percentage of the content on the web so that it is searchable.  ... 
doi:10.1007/3-540-47952-x_27 fatcat:c7hlep3wpjawpgldncxdcewzwe

Acquiring Comparative Commonsense Knowledge from the Web

Niket Tandon, Gerard Melo, Gerhard Weikum
2014 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
In this paper, we first rely on open information extraction methods to obtain large amounts of comparisons from the Web.  ...  Experiments show that our model outperforms strong baselines and allows us to obtain a large knowledge base of disambiguated commonsense assertions.  ...  We present the first open information extraction system for harvesting large amounts of comparative knowledge from Web contents. 2.  ... 
doi:10.1609/aaai.v28i1.8735 fatcat:wnmmd34zqjhp5d2ubjiprs6khi

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

Yubo Xie, Pearl Pu
2021 arXiv   pre-print
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  ...  In this paper, we give an overview of commonsense reasoning in natural language processing, which requires a deeper understanding of the contexts and usually involves inference over implicit external knowledge  ...  ., 2017] is a large-scale commonsense knowledge base that was automatically extracted and disambiguated from Web contents, using semi-supervised label propagation over graphs of noisy candidate assertions  ... 
arXiv:2108.04674v1 fatcat:feap4jp4mrhbdfhldylzltpota

Advanced Semantics for Commonsense Knowledge Extraction [article]

Tuan-Phong Nguyen, Simon Razniewski, Gerhard Weikum
2021 arXiv   pre-print
This paper presents a methodology, called Ascent, to automatically build a large-scale knowledge base (KB) of CSK assertions, with advanced expressiveness and both better precision and recall than prior  ...  Commonsense knowledge (CSK) about concepts and their properties is useful for AI applications such as robust chatbots.  ...  We present the Ascent method for acquiring CSK assertions with advanced semantics, from web contents.  ... 
arXiv:2011.00905v2 fatcat:ue2t2nbzbrfprctwtlfgzmzlmi

Advanced Semantics for Commonsense Knowledge Extraction

Tuan-Phong Nguyen, Simon Razniewski, Gerhard Weikum
2021 Proceedings of the Web Conference 2021  
This paper presents a methodology, called Ascent, to automatically build a large-scale knowledge base (KB) of CSK assertions, with advanced expressiveness and both better precision and recall than prior  ...  Commonsense knowledge (CSK) about concepts and their properties is useful for AI applications such as robust chatbots.  ...  We present the Ascent method for acquiring CSK assertions with advanced semantics, from web contents.  ... 
doi:10.1145/3442381.3449827 fatcat:iuavmpxgavaxtdrii52fpdb5cu

Open Mind Common Sense: Knowledge Acquisition from the General Public [chapter]

Push Singh, Thomas Lin, Erik T. Mueller, Grace Lim, Travell Perkins, Wan Li Zhu
2002 Lecture Notes in Computer Science  
Open Mind Common Sense is a knowledge acquisition system designed to acquire commonsense knowledge from the general public over the web.  ...  We describe and evaluate our first fielded system, which enabled the construction of a 450,000 assertion commonsense knowledge base.  ...  Acknowledgements We extend our thanks to David Stork for organizing the larger Open Mind effort, and the many thousands of members of the general public who contributed their knowledge to our database.  ... 
doi:10.1007/3-540-36124-3_77 fatcat:2sykukhuzbayzizpaacnhj2prq

Commonsense in Parts: Mining Part-Whole Relations from the Web and Image Tags

Niket Tandon, Charles Hariman, Jacopo Urbani, Anna Rohrbach, Marcus Rohrbach, Gerhard Weikum
2016 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
This paper presents a new method for automatically acquiring part-whole commonsense from Web contents and image tags at an unprecedented scale, yielding many millions of assertions, while specifically  ...  Commonsense knowledge about part-whole relations (e.g., screen partOf notebook) is important for interpreting user input in web search and question answering, or for object detection in images.  ...  As future work, we aim to extract facts from additional languages and an even wider range of Web contents.  ... 
doi:10.1609/aaai.v30i1.9992 fatcat:w66zpm7csfbgrefge7drlb7yia

Commonsense reasoning and commonsense knowledge in artificial intelligence

Ernest Davis, Gary Marcus
2015 Communications of the ACM  
Large-scale knowledge bases and Web mining have focused on taxonomic and statistical reasoning.  ...  , Frames, Case-based reasoning Large-scale CYC Knowledge based Math-based Informal Large-scale Web mining Crowd sourcing Architecture Substantial Little Substantial Moderate Little  ... 
doi:10.1145/2701413 fatcat:tc4gobnmxrdxrjv6e5toax6elq

GPU-based Commonsense Paradigms Reasoning for Real-Time Query Answering and Multimodal Analysis [article]

Nguyen Ha Tran, Erik Cambria
2018 arXiv   pre-print
We utilize commonsense knowledge bases to address the problem of real- time multimodal analysis.  ...  In addition, in order to ex- tract important textual features from multimodal sources we generate domain-specific graphs based on commonsense knowledge and apply GPU-based graph traversal for fast feature  ...  These issues are also crucial problems of querying and reasoning over large-scale commonsense knowledge bases (KBs).  ... 
arXiv:1807.08804v1 fatcat:xu5m2oh55ndahct7rtrbecjz3m

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.  ...  In fact, the presented application permits to leverage a large-scale commonsense knowledge base for annotating video by using semantic concepts.  ... 
doi:10.1007/978-3-642-31782-8_7 dblp:series/tanlp/CataldiDLP13 fatcat:ospnwo57nbh2dkcak3sh4wqnna

WebChild

Niket Tandon, Gerard de Melo, Fabian Suchanek, Gerhard Weikum
2014 Proceedings of the 7th ACM international conference on Web search and data mining - WSDM '14  
This paper presents a method for automatically constructing a large commonsense knowledge base, called WebChild 1 , from Web contents.  ...  We automatically derive seeds from WordNet and by pattern matching from Web text collections.  ...  This paper presents WebChild, a large commonsense KB automatically built from Web sources by a novel method relying on semi-supervised learning.  ... 
doi:10.1145/2556195.2556245 dblp:conf/wsdm/TandonMSW14 fatcat:ooxepfhqdzbtjmoldkm4mdkf2a

Commonsense Properties from Query Logs and Question Answering Forums [article]

Julien Romero, Simon Razniewski, Koninika Pal, Jeff Z. Pan, Archit Sakhadeo, Gerhard Weikum
2021 arXiv   pre-print
This paper presents Quasimodo, a methodology and tool suite for distilling commonsense properties from non-standard web sources.  ...  Commonsense knowledge about object properties, human behavior and general concepts is crucial for robust AI applications.  ...  RELATED WORK Commonsense Knowledge Bases (CSKB's). The most notable projects on building large commonsense knowledge bases are the following.  ... 
arXiv:1905.10989v4 fatcat:h2iuxuc7nvfudkycgvbqx5kxqy
« Previous Showing results 1 — 15 out of 2,241 results