Analogical Reasoning


Applications of Word Embeddings in NLP - DZone AI

#artificialintelligence

Word embeddings are basically a form of word representation that bridges the human understanding of language to that of a machine. Word embeddings are distributed representations of text in an n-dimensional space. These are essential for solving most NLP problems. Domain adaptation is a technique that allows Machine learning and Transfer Learning models to map niche datasets that are all written in the same language but are still linguistically different. For example, legal documents, customer survey responses, and news articles are all unique datasets that need to be analyzed differently.


Analogical Reasoning on Chinese Morphological and Semantic Relations

arXiv.org Artificial Intelligence

Analogical reasoning is effective in capturing linguistic regularities. This paper proposes an analogical reasoning task on Chinese. After delving into Chinese lexical knowledge, we sketch 68 implicit morphological relations and 28 explicit semantic relations. A big and balanced dataset CA8 is then built for this task, including 17813 questions. Furthermore, we systematically explore the influences of vector representations, context features, and corpora on analogical reasoning. With the experiments, CA8 is proved to be a reliable benchmark for evaluating Chinese word embeddings.


Book Reviews

AI Magazine

However, recently, there seems to be a new wave of interest, as indicated by many papers, monographs, edited books, and doctoral theses, in exploring aspects of similarity and analogical reasoning from various perspectives. Amid these numerous publications, Similarity and Analogical Reasoning surely stands out as the most valuable reference work on the topic, covering especially well the recent advances in the understanding of this topic, with many chapters written by leading researchers. Although it is based on a collection of papers initially presented at the Workshop on Similarity and Analogy, unlike the typical workshop proceedings, this volume is well edited and coherent in both its content and format, with a great deal of cross-references and detailed summary-comment chapters for every part of the book. Let us look at the book in detail. Because each of these chapters has a different perspective, approach, and organization, I first discuss a number of chapters one by one.


Making Artificial Intelligence to see the world that humans do

#artificialintelligence

A Northwestern University team developed a new computational model that performs at human levels on a standard intelligence test. This work is an important step toward making artificial intelligence systems that see and understand the world as humans do. "The model performs in the 75th percentile for American adults, making it better than average," said Northwestern Engineering's Ken Forbus. "The problems that are hard for people are also hard for the model, providing additional evidence that its operation is capturing some important properties of human cognition."The The platform has the ability to solve visual problems and understand sketches in order to give immediate, interactive feedback.


Making AI systems that see the world as humans do

#artificialintelligence

A Northwestern University team developed a new computational model that performs at human levels on a standard intelligence test. This work is an important step toward making artificial intelligence systems that see and understand the world as humans do. "The model performs in the 75th percentile for American adults, making it better than average," said Northwestern Engineering's Ken Forbus. "The problems that are hard for people are also hard for the model, providing additional evidence that its operation is capturing some important properties of human cognition." The new computational model is built on CogSketch, an artificial intelligence platform previously developed in Forbus' laboratory.


New Artificial Intelligence robots to mimic human cognition

#artificialintelligence

A team of artificial intelligence researchers from Northwestern University have built a robot on CogSketch model that will mimic the understanding level of common human beings. This computational model of analogy is based on the structure mapping theory of Northwestern psychology professor Dedre Gentner and the same artificial intelligence platform was previously developed in Forbus' Laboratory. According to Ken Forbus this model has the ability to understand the world as adult Americans do with an accuracy of 75 percentages. He further added that the things those are difficult for humans to understand are also difficult to recognise by these robots; best proof that it is mimicking human cognition. However; it can solve complex visual problems citing as one of the hallmarks of human intelligence.


Making AI systems that see the world as humans do

#artificialintelligence

A Northwestern University team developed a new computational model that performs at human levels on a standard intelligence test. This work is an important step toward making artificial intelligence systems that see and understand the world as humans do. "The model performs in the 75th percentile for American adults, making it better than average," said Northwestern Engineering's Ken Forbus. "The problems that are hard for people are also hard for the model, providing additional evidence that its operation is capturing some important properties of human cognition." The new computational model is built on CogSketch, an artificial intelligence platform previously developed in Forbus' laboratory.


Making computers reason and learn by analogy: Structure-mapping engine enables computers to reason and learn like humans, including solving moral dilemmas

#artificialintelligence

Using cognitive science theories, Forbus and his collaborators have developed a model that could give computers the ability to reason more like humans and even make moral decisions. Called the structure-mapping engine (SME), the new model is capable of analogical problem solving, including capturing the way humans spontaneously use analogies between situations to solve moral dilemmas. "In terms of thinking like humans, analogies are where it's at," said Forbus, Walter P. Murphy Professor of Electrical Engineering and Computer Science in Northwestern's McCormick School of Engineering. "Humans use relational statements fluidly to describe things, solve problems, indicate causality, and weigh moral dilemmas." The theory underlying the model is psychologist Dedre Gentner's structure-mapping theory of analogy and similarity, which has been used to explain and predict many psychology phenomena.


Interactive Learning and Analogical Chaining for Moral and Commonsense Reasoning

AAAI Conferences

Autonomous systems must consider the moral ramifications of their actions. Moral norms vary among people and depend on common sense, posing a challenge for encoding them explicitly in a system. I propose to develop a model of repeated analogical chaining and analogical reasoning to enable autonomous agents to interactively learn to apply common sense and model an individual’s moral norms.


Moral Decision-Making by Analogy: Generalizations versus Exemplars

AAAI Conferences

Moral reasoning is important to accurately model as AI systems become ever more integrated into our lives. Moral reasoning is rapid and unconscious; analogical reasoning, which can be unconscious, is a promising approach to model moral reasoning. This paper explores the use of analogical generalizations to improve moral reasoning. Analogical reasoning has already been used to successfully model moral reasoning in the MoralDM model, but it exhaustively matches across all known cases, which is computationally intractable and cognitively implausible for human-scale knowledge bases. We investigate the performance of an extension of MoralDM to use the MAC/FAC model of analogical retrieval over three conditions, across a set of highly confusable moral scenarios.