scholarly journals An experimental study measuring human annotator categorization agreement on commonsense sentences

2021 ◽  
Vol 2 ◽  
Author(s):  
Henrique Santos ◽  
Mayank Kejriwal ◽  
Alice M. Mulvehill ◽  
Gretchen Forbush ◽  
Deborah L. McGuinness
Keyword(s):  
Experimental Study ◽  
Recent Book ◽  
Commonsense Reasoning ◽  
Abstract Concepts ◽  
Important Goal ◽  
Commonsense Knowledge ◽  
Computational Theory ◽  
Fundamental Research ◽  
External Organization ◽  
Human Annotator

Abstract Developing agents capable of commonsense reasoning is an important goal in Artificial Intelligence (AI) research. Because commonsense is broadly defined, a computational theory that can formally categorize the various kinds of commonsense knowledge is critical for enabling fundamental research in this area. In a recent book, Gordon and Hobbs described such a categorization, argued to be reasonably complete. However, the theory’s reliability has not been independently evaluated through human annotator judgments. This paper describes such an experimental study, whereby annotations were elicited across a subset of eight foundational categories proposed in the original Gordon-Hobbs theory. We avoid bias by eliciting annotations on 200 sentences from a commonsense benchmark dataset independently developed by an external organization. The results show that, while humans agree on relatively concrete categories like time and space, they disagree on more abstract concepts. The implications of these findings are briefly discussed.

scholarly journals Logical Formalizations of Commonsense Reasoning: A Survey

2017 ◽  
Vol 59 ◽  
pp. 651-723 ◽  
Author(s):  
Ernest Davis
Keyword(s):  
Artificial Intelligence ◽  
Central Problem ◽  
Logical Inference ◽  
Commonsense Reasoning ◽  
Commonsense Knowledge ◽  
Artificial Intelligence Research ◽  
Representation Language

Commonsense reasoning is in principle a central problem in artificial intelligence, but it is a very difficult one. One approach that has been pursued since the earliest days of the field has been to encode commonsense knowledge as statements in a logic-based representation language and to implement commonsense reasoning as some form of logical inference. This paper surveys the use of logic-based representations of commonsense knowledge in artificial intelligence research.

Welcome to Wales: Searle on the Computational Theory of Mind

1995 ◽  
Vol 38 ◽  
pp. 85-97
Author(s):  
Roger Fellows
Keyword(s):  
Artificial Intelligence ◽  
Blood Flow ◽  
Theory Of Mind ◽  
Cognitive Science ◽  
Recent Book ◽  
Computational Theory Of Mind ◽  
Computational Theory ◽  
Linguistic Understanding ◽  
Flow Through ◽  
Computational Processes

In a recent book devoted to giving an overview of cognitive science, Justin Lieber writes:…dazzingly complex computational processes achieve our visual and linguistic understanding, but apart from a few levels of representation these are as little open to our conscious view as the multitudinous rhythm of blood flow through the countless vessels of our brain.It is the aim of hundreds of workers in the allied fields of Cognitive Science and Artificial Intelligence to unmask these computation processes and install them in digital computers.

scholarly journals Bridging Commonsense Reasoning and Probabilistic Planning via a Probabilistic Action Language

2019 ◽  
Vol 19 (5-6) ◽  
pp. 1090-1106
Author(s):  
YI WANG ◽  
SHIQI ZHANG ◽  
JOOHYUNG LEE
Keyword(s):  
Planning Under Uncertainty ◽  
Commonsense Reasoning ◽  
Sequential Decision ◽  
Unified Framework ◽  
Probabilistic Planning ◽  
Commonsense Knowledge ◽  
Action Languages ◽  
Action Language ◽  
Markov Decision ◽  
Probabilistic Action

AbstractTo be responsive to dynamically changing real-world environments, an intelligent agent needs to perform complex sequential decision-making tasks that are often guided by commonsense knowledge. The previous work on this line of research led to the framework called interleaved commonsense reasoning and probabilistic planning (icorpp), which used P-log for representing commmonsense knowledge and Markov Decision Processes (MDPs) or Partially Observable MDPs (POMDPs) for planning under uncertainty. A main limitation of icorpp is that its implementation requires non-trivial engineering efforts to bridge the commonsense reasoning and probabilistic planning formalisms. In this paper, we present a unified framework to integrate icorpp’s reasoning and planning components. In particular, we extend probabilistic action language pBC+ to express utility, belief states, and observation as in POMDP models. Inheriting the advantages of action languages, the new action language provides an elaboration tolerant representation of POMDP that reflects commonsense knowledge. The idea led to the design of the system pbcplus2pomdp, which compiles a pBC+ action description into a POMDP model that can be directly processed by off-the-shelf POMDP solvers to compute an optimal policy of the pBC+ action description. Our experiments show that it retains the advantages of icorpp while avoiding the manual efforts in bridging the commonsense reasoner and the probabilistic planner.

Applying Commonsense Reasoning to Place Identification

2010 ◽  
Vol 1 (2) ◽  
pp. 36-53 ◽  
Author(s):  
Marco Mamei
Keyword(s):  
Artificial Intelligence ◽  
Mobile Computing ◽  
Real Data ◽  
User Profile ◽  
Gps Data ◽  
Commonsense Reasoning ◽  
Artificial Intelligence System ◽  
Commonsense Knowledge ◽  
Intelligence System ◽  
Place Identification

Recent mobile computing applications try to automatically identify the places visited by the user from a log of GPS readings. Such applications reverse geocode the GPS data to discover the actual places (shops, restaurants, etc.) where the user has been. Unfortunately, because of GPS errors, the actual addresses and businesses being visited cannot be extracted unambiguously and often only a list of candidate places can be obtained. Commonsense reasoning can notably help the disambiguation process by invalidating some unlikely findings (e.g., a user visiting a cinema in the morning). This paper illustrates the use of Cyc—an artificial intelligence system comprising a database of commonsense knowledge—to improve automatic place identification. Cyc allows to probabilistically rank the list of candidate places in consideration of the commonsense likelihood of that place being actually visited on the basis of the user profile, the time of the day, what happened before, and so forth. The system has been evaluated using real data collected from a mobile computing application.

It’s in My Bones

2020 ◽  
pp. 131-149
Author(s):  
Iris Berent
Keyword(s):  
Embodied Cognition ◽  
The Body ◽  
Computational Theory Of Mind ◽  
Abstract Concepts ◽  
Computational Theory ◽  
Bodily Experiences ◽  
Abstract Notion ◽  
The Mind ◽  
Material Bodies

When I point to an object, you and I can agree on what it is (a red, round cup). How does our brain (matter) represent such notions? And how do we (distinct material bodies) apparently converge so we can talk about the same things? Cognitive scientists and philosophers have long assumed that people share abstract concepts (e.g., a cup); to explain how such abstract concepts can give rise to thinking, they further proposed the computational theory of mind. But theories of “embodied cognition” assert that cognition is all “in people’s bones.” What we know as a cup is not an abstract notion but rather the bodily experiences of our sensory and motor interactions with a cup—its shiny color, how it feels in our hands, the smoothness of its surface, its weight, and shape. I suggest that “Embodiment” is alluring because it promises to resolve the mysteries of Dualism (how can material bodies encode the immaterial notion of a cup?) and the origins of ideas (how do we all converge on an understanding that allows us to talk about the same things?). The solution is strikingly simple—just remove the “mind” from the equation. If there is no (immaterial) knowledge, then we no longer need to worry about how knowledge arises from the body and how knowledge can be learned. As discussed in the previous chapter, people erroneously believe that “if it’s in my body” then “it’s inborn.” Dualism and essentialism thus explain some of the lure of embodied cognition.

scholarly journals MITRE at SemEval-2018 Task 11: Commonsense Reasoning without Commonsense Knowledge

2018 ◽  
Author(s):  
Elizabeth Merkhofer ◽  
John Henderson ◽  
David Bloom ◽  
Laura Strickhart ◽  
Guido Zarrella
Keyword(s):  
Commonsense Reasoning ◽  
Commonsense Knowledge

Applying Commonsense Reasoning to Place Identification

2012 ◽  
pp. 951-968
Author(s):  
Marco Mamei
Keyword(s):  
Artificial Intelligence ◽  
Mobile Computing ◽  
Real Data ◽  
User Profile ◽  
Gps Data ◽  
Commonsense Reasoning ◽  
Artificial Intelligence System ◽  
Commonsense Knowledge ◽  
Intelligence System ◽  
Place Identification

Recent mobile computing applications try to automatically identify the places visited by the user from a log of GPS readings. Such applications reverse geocode the GPS data to discover the actual places (shops, restaurants, etc.) where the user has been. Unfortunately, because of GPS errors, the actual addresses and businesses being visited cannot be extracted unambiguously and often only a list of candidate places can be obtained. Commonsense reasoning can notably help the disambiguation process by invalidating some unlikely findings (e.g., a user visiting a cinema in the morning). This paper illustrates the use of Cyc—an artificial intelligence system comprising a database of commonsense knowledge—to improve automatic place identification. Cyc allows to probabilistically rank the list of candidate places in consideration of the commonsense likelihood of that place being actually visited on the basis of the user profile, the time of the day, what happened before, and so forth. The system has been evaluated using real data collected from a mobile computing application.

Applying Commonsense Reasoning to Place Identification

2012 ◽  
pp. 124-140
Author(s):  
Marco Mamei
Keyword(s):  
Artificial Intelligence ◽  
Mobile Computing ◽  
Real Data ◽  
User Profile ◽  
Gps Data ◽  
Commonsense Reasoning ◽  
Artificial Intelligence System ◽  
Commonsense Knowledge ◽  
Intelligence System ◽  
Place Identification

Recent mobile computing applications try to automatically identify the places visited by the user from a log of GPS readings. Such applications reverse geocode the GPS data to discover the actual places (shops, restaurants, etc.) where the user has been. Unfortunately, because of GPS errors, the actual addresses and businesses being visited cannot be extracted unambiguously and often only a list of candidate places can be obtained. Commonsense reasoning can notably help the disambiguation process by invalidating some unlikely findings (e.g., a user visiting a cinema in the morning). This paper illustrates the use of Cyc—an artificial intelligence system comprising a database of commonsense knowledge—to improve automatic place identification. Cyc allows to probabilistically rank the list of candidate places in consideration of the commonsense likelihood of that place being actually visited on the basis of the user profile, the time of the day, what happened before, and so forth. The system has been evaluated using real data collected from a mobile computing application.

scholarly journals Using Answer Set Programming for Commonsense Reasoning in the Winograd Schema Challenge

2019 ◽  
Vol 19 (5-6) ◽  
pp. 1021-1037
Author(s):  
ARPIT SHARMA
Keyword(s):  
Natural Language ◽  
Answer Set Programming ◽  
Natural Language Understanding ◽  
Turing Test ◽  
Subgraph Isomorphism ◽  
Commonsense Reasoning ◽  
Language Understanding ◽  
Commonsense Knowledge ◽  
Additional Constraints ◽  
Answer Set

AbstractThe Winograd Schema Challenge (WSC) is a natural language understanding task proposed as an alternative to the Turing test in 2011. In this work we attempt to solve WSC problems by reasoning with additional knowledge. By using an approach built on top of graph-subgraph isomorphism encoded using Answer Set Programming (ASP) we were able to handle 240 out of 291 WSC problems. The ASP encoding allows us to add additional constraints in an elaboration tolerant manner. In the process we present a graph based representation of WSC problems as well as relevant commonsense knowledge.

Sign in / Sign up

Export Citation Format

Share Document