Distances between Predicates in By-Analogy Reasoning Systems

The purpose is to develop expert systems where by-analogy reasoning is used. Knowledge “closeness” problems are known to frequently emerge in such systems if knowledge is represented by different production rules. To determine a degree of closeness for production rules a distance between predicates is introduced. Different types of distances between two predicate value distribution functions are considered when predicates are “true”. Asymptotic features and interrelations of distances are studied. Predicate value distribution functions are found by empirical distribution functions, and a procedure is proposed for this purpose. An adequacy of obtained distribution functions is tested on the basis of the statistical 2 χ –criterion and a testing mechanism is discussed. A theorem, by which a simple procedure of measurement of Euclidean distances between distribution function parameters is substituted for a predicate closeness determination one, is proved for parametric distribution function families. The proposed distance measurement apparatus may be applied in expert systems when reasoning is created by analogy.

Reasoning by Structural Analogy Taking into Account the Context for Intelligent Decision Support Systems

Development of methods and tools for modeling human reasoning (common sense reasoning) by analogy in intelligent decision support systems is considered. Special attention is drawn to modeling reasoning by structural analogy taking the context into account. The possibility of estimating the obtained analogies taking into account the context is studied. This work was supported by RFBR.

Teaching and using analogy in law

Analogy plays a central role in legal reasoning, yet how to analogize is poorly taught and poorly practiced. We all recognize when legal analogies are being made: when a law professor suggests a difficult hypothetical in class and a student tentatively guesses at the answer based on the cases she read the night before, when an attorney advises a client to settle because a previous case goes against him, or when a judge adopts one precedent over another on the basis that it better fits the present case. However, when it comes to explaining why certain analogies are compelling, persuasive, or better than the alternative, lawyers usually draw a blank. The purpose of this article is to provide a simple model that can be used to teach and to learn how analogy actually works, and what makes one analogy superior to a competing analogy. The model is drawn from a number of theories of analogy making in cognitive science. Cognitive science is the “long-term enterprise to understand the mind scientifically.” The field studies the mechanisms that are involved in cognitive processes like thinking, memory, learning, and recall; and one of its main foci has been on how people construct analogies. The lessons from cognitive science theories of analogy can be applied to legal analogies to give students and lawyers a better understanding of this fundamental process in legal reasoning.

Reason is too large : analogy and precedent in law

Hunter argues that cognitive science models of human thinking explain how analogical reasoning and precedential reasoning operate in law. He offers an explanation of why various legal theories are so limited and calls for greater attention to what is actually happening when lawyers and judges reason, by analogy, with precedent.

Analogical reasoning in case-based design

A computer can assist the process of design by analogy by recording past designs. The experience these represent could be much wider than that of designers using the system, who therefore need to identify potential cases of interest. If the computer assists with this lookup, the designers can concentrate on the more interesting aspect of extracting and using the ideas which are found. However, as the knowledge base grows it becomes ever harder to find relevant cases using a keyword indexing scheme without knowing precisely what to look for. Therefore a more flexible searching system is needed.

If a similarity measure can be defined for the features of the designs, then it is possible to match and cluster them. Using a simple measure like co-occurrence of features within a particular case would allow this to happen without human intervention, which is tedious and time- consuming. Any knowledge that is acquired about how features are related to each other will be very shallow: it is not intended as a cognitive model for how humans understand, learn, or retrieve information, but more an attempt to make effective, efficient use of the information available. The question remains of whether such shallow knowledge is sufficient for the task.

A system to retrieve information from a large database is described. It uses co-occurrences to relate keywords to each other, and then extends search queries with similar words. This seems to make relevant material more accessible, providing hope that this retrieval technique can be applied to a broader knowledge base.

Use of Analogy to Achieve New Expertise

We will take the view that the end result of problem solving in some world should be increased expertness. In the context of computers, increasing expertness means writing programs. This thesis is about a process, reasoning by analogy that writes programs. Analogy relates one problem world to another. We will call the world in which we have an expert problem solver the IMAGE world, and the other world the DOMAIN world. Analogy will construct an expert problem solver in the domain world using the image world expert for inspiration.

Analogy in Decision-Making

In the context of decision making under uncertainty, we formalize the concept of analogy: an analogy between two decision problems is a mapping that transforms one problem into the other while preserving the problem's structure. We identify the basic structure of a decision problem, and provide a representation of the mappings that pre- serve this structure. We then consider decision makers who use multiple analogies. Our main results are a representation theorem for "aggregators" of analogies satisfying certain minimal requirements, and the identification of preferences emerging from analogical reasoning. We show that a large variety of multiple-prior preferences can be thought of as emerging from analogical reasoning.

Using Analogy to Acquire Commonsense Knowledge from Human Contributors

The goal of the work reported here is to capture the commonsense knowledge of non-expert human contributors. Achieving this goal will enable more intelligent human-computer interfaces and pave the way for computers to reason about our world. In the domain of natural language processing, it will provide the world knowledge much needed for semantic processing of natural language. To acquire knowledge from contributors not trained in knowledge engineering, I take the following four steps: (i) develop a knowledge representation (KR) model for simple assertions in natural language, (ii) introduce cumulative analogy, a class of nearest-neighbor based analogical reasoning algorithms over this representation, (iii) argue that cumulative analogy is well suited for knowledge acquisition (KA) based on a theoretical analysis of effectiveness of KA with this approach, and (iv) test the KR model and the effectiveness of the cumulative analogy algorithms empirically. To investigate effectiveness of cumulative analogy for KA empirically, Learner, an open source system for KA by cumulative analogy has been implemented, deployed, and evaluated. (The site "1001 Questions," is available at http://teach-computers.org/learner.html). Learner acquires assertion-level knowledge by constructing shallow semantic analogies between a KA topic and its nearest neighbors and posing these analogies as natural language questions to human contributors. Suppose, for example, that based on the knowledge about "newspapers" already present in the knowledge base, Learner judges "newspaper" to be similar to "book" and "magazine." Further suppose that assertions "books contain information" and "magazines contain information" are also already in the knowledge base. Then Learner will use cumulative analogy from the similar topics to ask humans whether "newspapers contain information." Because similarity between topics is computed based on what is already known about them, Learner exhibits bootstrapping behavior --- the quality of its questions improves as it gathers more knowledge. By summing evidence for and against posing any given question, Learner also exhibits noise tolerance, limiting the effect of incorrect similarities. The KA power of shallow semantic analogy from nearest neighbors is one of the main findings of this thesis. I perform an analysis of commonsense knowledge collected by another research effort that did not rely on analogical reasoning and demonstrate that indeed there is sufficient amount of correlation in the knowledge base to motivate using cumulative analogy from nearest neighbors as a KA method. Empirically, evaluating the percentages of questions answered affirmatively, negatively and judged to be nonsensical in the cumulative analogy case compares favorably with the baseline, no-similarity case that relies on random objects rather than nearest neighbors. Of the questions generated by cumulative analogy, contributors answered 45% affirmatively, 28% negatively and marked 13% as nonsensical; in the control, no-similarity case 8% of questions were answered affirmatively, 60% negatively and 26% were marked as nonsensical.

Analogous Reasoning and Case-based Reasoning for Intelligent Decision Support Systems

Methods of analogous reasoning and case-based reasoning for intelligent decision support systems are considered. Special attention is drawn to methods based on a structural analogy that take the context into account. This work was supported by RFBR (projects 02-07-90042, 05-07-90232).

SEEKING CULTURAL FAIRNESS IN A MEASURE OF RELATIONAL REASONING

Relational reasoning, or the ability to identify meaningful patterns within any stream of information, is a fundamental cognitive ability associated with academic success across a variety of domains of learning and levels of schooling. However, the measurement of this construct has been historically problematic. For example, while the construct is typically described as multidimensional—including the identification of multiple types of higher-order patterns—it is most often measured in terms of a single type of pattern: analogy. For that reason, the Test of Relational Reasoning (TORR) was conceived and developed to include three other types of patterns that appear to be meaningful in the educational context: anomaly, antinomy, and antithesis. Moreover, as a way to focus on fluid relational reasoning ability, the TORR was developed to include, except for the directions, entirely visuo-spatial stimuli, which were designed to be as novel as possible for the participant. By focusing on fluid intellectual processing, the TORR was also developed to be fairly administered to undergraduate students—regardless of the particular gender, language, and ethnic groups they belong to. However, although some psychometric investigations of the TORR have been conducted, its actual fairness across those demographic groups has yet to be empirically demonstrated. Therefore, a systematic investigation of differential-item-functioning (DIF) across demographic groups on TORR items was conducted. A large (N = 1,379) sample, representative of the University of Maryland on key demographic variables, was collected, and the resulting data was analyzed using a multi-group, multidimensional item-response theory model comparison procedure. Using this procedure, no significant DIF was found on any of the TORR items across any of the demographic groups of interest. This null finding is interpreted as evidence of the cultural-fairness of the TORR, and potential test-development choices that may have contributed to that cultural-fairness are discussed. For example, the choice to make the TORR an untimed measure, to use novel stimuli, and to avoid stereotype threat in test administration, may have contributed to its cultural-fairness. Future steps for psychometric research on the TORR, and substantive research utilizing the TORR, are also presented and discussed.

Relations among Topic Knowledge, Individual Interest, and Relational Reasoning, and Critical Thinking in Maternity Nursing

Critical thinking in learners is a goal of educators and professional organizations in nursing as well as other professions. However, few studies in nursing have examined the role of the important individual difference factors topic knowledge, individual interest, and general relational reasoning strategies in predicting critical thinking. In addition, most previous studies have used domain-general, standardized measures, with inconsistent results. Moreover, few studies have investigated critical thinking across multiple levels of experience. The major purpose of this study was to examine the degree to which topic knowledge, individual interest, and relational reasoning predict critical thinking in maternity nurses. For this study, 182 maternity nurses were recruited from national nursing listservs explicitly chosen to capture multiple levels of experience from prelicensure to very experienced nurses. The three independent measures included a domain-specific Topic Knowledge Assessment (TKA), consisting of 24 short-answer questions, a Professed and Engaged Interest Measure (PEIM), with 20 questions indicating level of interest and engagement in maternity nursing topics and activities, and the Test of Relational Reasoning (TORR), a graphical selected response measure with 32 items organized in scales corresponding to four forms of relational reasoning: analogy, anomaly, antithesis, and antinomy. The dependent measure was the Critical Thinking Task in Maternity Nursing (CT2MN), composed of a clinical case study providing cues with follow-up questions relating to nursing care. These questions align with the cognitive processes identified in a commonly-used definition of critical thinking in nursing. Reliable coding schemes for the measures were developed for this study. Key findings included a significant correlation between topic knowledge and individual interest. Further, the three individual difference factors explained a significant proportion of the variance in critical thinking with a large effect size. While topic knowledge was the strongest predictor of critical thinking performance, individual interest had a moderate significant effect, and relational reasoning had a small but significant effect. The findings suggest that these individual difference factors should be included in future studies of critical thinking in nursing. Implications for nursing education, research, and practice are discussed.