Arrow Research search

Author name cluster

Ernest Davis

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

25 papers
2 author rows

Possible papers

25

AAAI Conference 2024 Conference Paper

The Defeat of the Winograd Schema Challenge (Abstract Reprint)

  • Vid Kocijan
  • Ernest Davis
  • Thomas Lukasiewicz
  • Gary Marcus
  • Leora Morgenstern

The Winograd Schema Challenge—a set of twin sentences involving pronoun reference disambiguation that seem to require the use of commonsense knowledge—was proposed by Hector Levesque in 2011. By 2019, a number of AI systems, based on large pre-trained transformer-based language models and fine-tuned on these kinds of problems, achieved better than 90% accuracy. In this paper, we review the history of the Winograd Schema Challenge and discuss the lasting contributions of the flurry of research that has taken place on the WSC in the last decade. We discuss the significance of various datasets developed for WSC, and the research community's deeper understanding of the role of surrogate tasks in assessing the intelligence of an AI system.

JAIR Journal 2017 Journal Article

Logical Formalizations of Commonsense Reasoning: A Survey

  • Ernest Davis

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.

KR Conference 2012 Conference Paper

The Winograd Schema Challenge

  • Hector Levesque
  • Ernest Davis
  • Leora Morgenstern

ing the presence of thinking (or understanding, or intelligence, or whatever appropriate mental attribute), we assume that typed English text, despite its limitations, will be a rich enough medium. In this paper, we present an alternative to the Turing Test that has some conceptual and practical advantages. A Winograd schema is a pair of sentences that differ only in one or two words and that contain a referential ambiguity that is resolved in opposite directions in the two sentences. We have compiled a collection of Winograd schemas, designed so that the correct answer is obvious to the human reader, but cannot easily be found using selectional restrictions or statistical techniques over text corpora. A contestant in the Winograd Schema Challenge is presented with a collection of one sentence from each pair, and required to achieve human-level accuracy in choosing the correct disambiguation. 1 2 The trouble with Turing The Turing Test does have some troubling aspects, however. First, note the central role of deception. Consider the case of a future intelligent machine trying to pass the test. It must converse with an interrogator and not just show its stuff, but fool her into thinking she is dealing with a person. This is just a game, of course, so it’s not really lying. But to imitate a person well without being evasive, the machine will need to assume a false identity (to answer “How tall are you? ” or “Tell me about your parents. ”). All other things being equal, we should much prefer a test that did not depend on chicanery of this sort. Or to put it differently, a machine should be able to show us that it is thinking without having to pretend to be somebody or to have some property (like being tall) that it does not have. We might also question whether a conversation in English is the right sort of test. Free-form conversations are no doubt the best way to get to know someone, to find out what they think about something, and therefore that they are thinking about something. But conversations are so adaptable and can be so wide-ranging that they facilitate deception and trickery. Consider, for example, ELIZA (Weizenbaum 1966), where a program (usually included as part of the normal Emacs distribution), using very simple means, was able to fool some people into believing they were conversing with a psychiatrist. The deception works at least in part because we are extremely forgiving in terms of what we will accept as legitimate conversation. A Rogerian psychiatrist may say very little except to encourage a patient to keep on talking, but it may be enough, at least for a while. Consider also the Loebner competition (Shieber 1994), a restricted version of the Turing Test that has attracted considerable publicity. In this case, we have a more balanced conversation taking place than with ELIZA. What is striking about transcripts of these conversations is the fluidity of the responses from the subjects: elaborate wordplay, puns, jokes, quotations, clever asides, emotional outbursts, points of order. Everything, it would seem, except clear and direct

AAAI Conference 2010 Conference Paper

Ontologies and Representations of Matter

  • Ernest Davis

We carry out a comparative study of the expressive power of different ontologies of matter in terms of the ease with which simple physical knowledge can be represented. In particular, we consider five ontologies of models of matter: particle models, fields, two ontologies for continuous material, and a hybrid model. We evaluate these in terms of how easily eleven benchmark physical laws and scenarios can be represented.

KR Conference 2004 Conference Paper

A First-Order Theory of Communicating First-Order Formulas

  • Ernest Davis

This paper presents a theory of informative communications among agents that allows a speaker to communicate to a hearer truths about the state of the world; the occurrence of events, including other communicative acts; and the knowledge states of any agent --- speaker, hearer, or third parties --- any of these in the past, present, or future --- and any logical combination of these, including formulas with quantifiers. We prove that the theory is consistent and compatible with a wide range of physical theories. We examine how the theory avoids two potential paradoxes, and discuss how these paradoxes may post a danger when this theory is extended.

AAAI Conference 2004 Conference Paper

Continuous Time in a SAT-Based Planner

  • Ji-Ae Shin
  • Ernest Davis

The TM-LPSAT planner can construct plans in domains containing atomic actions and durative actions; events and processes; discrete, real-valued, and interval-valued fluents; and continuous linear change to quantities. It works in three stages. In the first stage, a representation of the domain and problem in an extended version of PDDL+ is compiled into a system of propositional combinations of propositional variables and linear constraints over numeric variables. In the second stage, the LPSAT constraint engine (Wolfman & Weld 2000) is used to find a solution to the system of constraints. In the third stage, a correct parallel plan is extracted from this solution. We discuss the structure of the planner and show how a real-time temporal model is compiled into LPSAT constraints.

ICAPS Conference 1994 Conference Paper

Branching Continuous Time and the Semantics of Continuous Action

  • Ernest Davis

D. Suppose that: It is often useful to model the behavior of an autonomousintelligent creature in terms of continuous control and choice. For example, a robot whomoves i through space can be idealized as able to execute any continuous motion, subject to constraints on veii locity and accelleration; in such a model, the robot can %hoose = at any instant to change his accelleriv ation. Weshow how such models can be described using a continuous branching time structure. Wediscuss mathematical foundations of continuous branching structures, theories of continuous action in physical worlds, embeddingof discrete theories of action E. L h in a continuous structure, and physical and epistemic feasibility of plans with continuousac! ion. (n Continuous Plans bi

IJCAI Conference 1985 Conference Paper

A Representation for Complex Physical Domains

  • Sanjaya Addanki
  • Ernest Davis

We are exploring a system, called PROMPT, that will be capable of reasoning from first principles and high level knowledge in complex, physical domains. Such problem-solving calls for a representation that will support the different analyses techniques required (e. g. differential, asymptotic, perturbation etc.). Efficiency considerations require that the representation also support heuristic control of reasoning techniques. This paper lays the ground work for our effort by briefly describing the ontology and the representation scheme of PROMPT. Our ontology allows reasoning about multiple pasts and different happenings in the same space-time. The ontology provides important distinctions between materials, objects, bulk and distributed abstractions among physical entities. We organise world knowledge into "prototypes" that are used to focus the reasoning process. Problem-solving involves reasoning with and modifying prototypes.