3,643 Hits in 3.9 sec

SP-10K: A Large-scale Evaluation Set for Selectional Preference Acquisition

Hongming Zhang, Hantian Ding, Yangqiu Song
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
To demonstrate the importance of our dataset, we investigate the relationship between SP-10K and the commonsense knowledge in ConceptNet5 and show the potential of using SP to represent the commonsense  ...  knowledge.  ...  We thank Victor Wing-chuen KWAN and other anonymous reviewers for their valuable comments and suggestions that help improving the quality of this paper.  ... 
doi:10.18653/v1/p19-1071 dblp:conf/acl/ZhangDS19 fatcat:j5pp2mehcff6biz5gkdkup5bdu

A Survey of Knowledge-Intensive NLP with Pre-Trained Language Models [article]

Da Yin, Li Dong, Hao Cheng, Xiaodong Liu, Kai-Wei Chang, Furu Wei, Jianfeng Gao
2022 arXiv   pre-print
including providing and making flexible use of encyclopedic and commonsense knowledge.  ...  In this paper, we aim to summarize the current progress of pre-trained language model-based knowledge-enhanced models (PLMKEs) by dissecting their three vital elements: knowledge sources, knowledge-intensive  ...  Even if we compose large-scale commonsense knowledge sources with the help of knowledge acquisition methods, we are still likely to miss a large body of commonsense knowledge used in our daily life.  ... 
arXiv:2202.08772v1 fatcat:zayodfdoq5gk7imgvo6awfadui

Towards an Atlas of Cultural Commonsense for Machine Reasoning [article]

Anurag Acharya, Kartik Talamadupula, Mark A Finlayson
2020 arXiv   pre-print
It also moves us a step closer towards building a machine that doesn't assume a rigid framework of universal (and likely Western-biased) commonsense knowledge, but rather has the ability to reason in a  ...  the identity of the groups providing the knowledge.  ...  We report on the results of the survey, and showcase what a truly cultural commonsense knowledge repository might look like.  ... 
arXiv:2009.05664v3 fatcat:zoy54p5hpjgr5me5p4mzdxmgcu

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  ...  A vast amount of work on commonsense knowledge acquisition and reasoning has traditionally been conducted in the knowledge representation and reasoning community (see Zang et al. (2013) for a survey)  ... 
arXiv:2201.12438v1 fatcat:tpqwhagvnvdzlhzmbm6ajhokcm

Recognizing expressions of commonsense psychology in English Text

Andrew Gordon, Abe Kazemzadeh, Anish Nair, Milena Petrova
2003 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - ACL '03  
In this paper, we describe our efforts to create a robust, large-scale lexical-semantic resource for the recognition and classification of expressions of commonsense psychology in English Text.  ...  We achieve high levels of precision and recall by hand-authoring sets of local grammars for commonsense psychology concepts, and show that this approach can achieve classification performance greater than  ...  Any opinions, findings and conclusions or recommendations expressed in this paper are those of the authors and do not necessarily reflect the views of the Department of the Army.  ... 
doi:10.3115/1075096.1075123 dblp:conf/acl/GordonKNP03 fatcat:bomlpnp24jgf5gil4kgqwarp7i

Beating Common Sense into Interactive Applications

Henry Lieberman, Hugo Liu, Push Singh, Barbara Barry
2004 The AI Magazine  
This article surveys several of these applications and reflects on interface design principles that enable successful use of commonsense knowledge.  ...  ■ A long-standing dream of artificial intelligence has been to put commonsense knowledge into computers-enabling machines to reason about everyday life.  ...  Our approach to knowledge acquisition was inspired by the success of information extraction methods (Cardie 1997) .  ... 
doi:10.1609/aimag.v25i4.1785 dblp:journals/aim/LiebermanLSB04 fatcat:bm6wkzaabrdi7mi4weti2qceii

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.  ...  Efforts to consolidate commonsense knowledge have yielded partial success, with no clear path towards a comprehensive solution.  ...  [38] survey knowledge graphs in terms of their representation principles, acquisition methods, and applications.  ... 
arXiv:2101.04640v2 fatcat:ehkp23l2cfelrm6urgmyiyyix4

A Survey of Knowledge-based Sequential Decision Making under Uncertainty [article]

Shiqi Zhang, Mohan Sridharan
2020 arXiv   pre-print
RDK methods reason with declarative domain knowledge, including commonsense knowledge, that is either provided a priori or acquired over time, while SDM methods (probabilistic planning and reinforcement  ...  learning) seek to compute action policies that maximize the expected cumulative utility over a time horizon; both classes of methods reason in the presence of uncertainty.  ...  Office of Naval Research Science of Autonomy Awards N00014-17-1-2434 and N00014-20-1-2390, and the Asian Office of Aerospace Research and Development award FA2386-16-1-4071.  ... 
arXiv:2008.08548v2 fatcat:5nj6moddanbwzmnldzaq6qp46e

Occupational risks, safety and masculinity: Newfoundland fish harvesters' experiences and understandings of fishery risks

Nicole Gerarda Power
2008 Health, Risk and Society  
best way to assess and minimize risk is through seeking input from a variety of different knowledge agents focusing on different sources and dimensions of risk and using multiple methodologies.  ...  There is a growing body of international literature describing the extent, severity and causes of occupational health and safety (OHS) risks associated with fishing work (Binkley  ...  This makes sense in light of recent trends that make difficult the acquisition or relevance of commonsense knowledge through established means, including the shift in target species and fishing location  ... 
doi:10.1080/13698570802167405 fatcat:2fm3wivc2fbr7eaeqcqaxtoqju

Natural Language QA Approaches using Reasoning with External Knowledge [article]

Chitta Baral, Pratyay Banerjee, Kuntal Kumar Pal, Arindam Mitra
2020 arXiv   pre-print
In this paper, we present a survey of the recent work on them.  ...  We believe our survey will help establish a bridge between multiple fields of AI, especially between (a) the traditional fields of knowledge representation and reasoning and (b) the field of NL understanding  ...  In the rest of the paper we present several aspects of building NLQA systems for such datasets and give a brief survey of the existing methods.  ... 
arXiv:2003.03446v1 fatcat:5ssmvcdzajc5flasg3s5hsfxsu

What Computers Should Know, Shouldn't Know, and Shouldn't Believe

Gerhard Weikum
2017 Proceedings of the 26th International Conference on World Wide Web Companion - WWW '17 Companion  
Automatically constructed knowledge bases (KB's) are a powerful asset for search, analytics, recommendations and data integration, with intensive use at big industrial stakeholders.  ...  These and other knowledge and data resources are interlinked at the entity level, forming the Web of Linked Open Data.  ...  This way of knowledge acquisition misses out on a number of important dimensions, posing open challenges for next-generation KB's.  ... 
doi:10.1145/3041021.3051120 dblp:conf/www/Weikum17 fatcat:p7npy54ugrf4lhtyifiyfa3g3q

Digital Intuition: Applying Common Sense Using Dimensionality Reduction

Catherine Havasi, Robyn Speer, James Pustejovsky, Henry Lieberman
2010 IEEE Intelligent Systems  
Acquiring and Representing Common Sense Open Mind Common Sense takes a distributed approach to the problem of commonsense knowledge acquisition.  ...  If you are interested in starting a commonsense knowledge acquisition project in your language, please contact us at conceptnet@media. using Open mind common Sense on the knowledge collection  ... 
doi:10.1109/mis.2010.4 fatcat:qcmgvubc5jabpkzura7rdnhmi4

Digital Intuition: Applying Common Sense Using Dimensionality Reduction

Catherine Havasi, Robyn Speer, James Pustejovsky, Henry Lieberman
2009 IEEE Intelligent Systems  
Acquiring and Representing Common Sense Open Mind Common Sense takes a distributed approach to the problem of commonsense knowledge acquisition.  ...  If you are interested in starting a commonsense knowledge acquisition project in your language, please contact us at conceptnet@media. using Open mind common Sense on the knowledge collection  ... 
doi:10.1109/mis.2009.84 fatcat:kar7re4p7fg4lgypxu44zxta7y

Commonsense Properties from Query Logs and Question Answering Forums

Julien Romero, Simon Razniewski, Koninika Pal, Jeff Z. Pan, Archit Sakhadeo, Gerhard Weikum
2019 Proceedings of the 28th ACM International Conference on Information and Knowledge Management - CIKM '19  
However, automatic acquisition of this knowledge is challenging because of sparseness and bias in online sources.  ...  This paper presents Quasimodo, a methodology and tool suite for distilling commonsense properties from non-standard web sources.  ...  Approach and Challenges This paper puts forward Quasimodo 2 , a framework and tool for scalable automatic acquisition of commonsense properties.  ... 
doi:10.1145/3357384.3357955 dblp:conf/cikm/RomeroRPPSW19 fatcat:idb3jc75gjc7tjpvog5zj3qoqm

Machine Common Sense Concept Paper [article]

David Gunning
2018 arXiv   pre-print
librarian, to construct a commonsense knowledge repository capable of answering natural language and image-based questions about commonsense phenomena.  ...  Machine common sense has long been a critical-but-missing component of Artificial Intelligence (AI).  ...  A 2015 survey of commonsense reasoning in AI summarized the major approaches taken in the past [1] , including the taxonomy of approaches shown in Figure 1 below.  ... 
arXiv:1810.07528v1 fatcat:pntbtkr7tfglxbdznb4t3inhsm
« Previous Showing results 1 — 15 out of 3,643 results