Previous systems for literature based discovery, an automatic method of identifying hidden knowledge, have largely been based on bag of words approaches which perform only limited semantic analysis and interpretation. We describe the shortcomings of these approaches and suggest possible solutions that make use of techniques from Natural Language Processing.

In this article some formal, content-related and procedural considerations towards the sense of humor are articulated and the analysis of both everyday humor behavior and of comic styles leads to the initial proposal of a four factor-model of humor (4FMH). This model is tested in a new dataset and it is also examined whether two forms of comic styles (benevolent humor and moral mockery) do fit in. The model seems to be robust but further studies on the structure of the sense of humor as a personality trait are required.

There is strong theoretical evidence that aggregation of human judgments should not simply average multiple forecasts together (the unweighted linear opinion pool, or ULinOP), but weight them in such a way as to insure representation of a maximally diverse set of models among the experts from whom they are elicited. Explicitly eliciting these models places a major burden on the experts. We report on a variety of approaches to estimating these models, or at least the diversity among them, with minimal explicit input from the experts.

This exercise in metatheory presents what any theory consists of and what properties it should have. It, then, adjust the general recipe to a theory of humor and computational humor. In this light, it reviews the state of the art in computational humor and suggests the main lines of development.

Intelligent systems promise to amplify, augment, and extend innate human abilities. A principal example is that of assistive rehabilitation robots---artificial intelligence and machine learning enable new electromechanical systems that restore biological functions lost through injury or illness. In order for an intelligent machine to assist a human user, it must be possible for a human to communicate their intentions and preferences to their non-human counterpart. While there are a number of techniques that a human can use to direct a machine learning system, most research to date has focused on the contrasting strategies of instruction and reward. The primary contribution of our work is to demonstrate that the middle ground between instruction and reward is a fertile space for research and immediate technological progress. To support this idea, we introduce the setting of human-prompted switching, and illustrate the successful combination of switching with interactive learning using a concrete real-world example: human control of a multi-joint robot arm. We believe techniques that fall between the domains of instruction and reward are complementary to existing approaches, and will open up new lines of rapid progress for interactive human training of machine learning systems.

We aim to identify and control unintentional humor occurring in human-computer interaction, and recreate it intentionally. In this research we focus on text prediction systems, a type of interactive programs employed in mobile phones, search engines, and word processors. More specifically, we identified two design principles, inspired by humor and emotion theories, and implemented them in a proof-of-concept tool simulating a specific type of text prediction.

Learning new motor tasks autonomously from interaction with a human being is an important goal for both robotics and machine learning. However, when moving beyond basic skills, most monolithic machine learning approaches fail to scale. In this paper, we take the task of learning table tennis as an example and present a new framework which allows a robot to learn cooperative table tennis from interaction with a human. Therefore, the robot first learns a set of elementary table tennis hitting movements from a human teacher by kinesthetic teach-in, which is compiled into a set of dynamical system motor primitives (DMPs). Subsequently, the system generalizes these movements to a wider range of situations using our mixture of motor primitives (MoMP) approach. The resulting policy enables the robot to select appropriate motor primitives as well as to generalize between them. Finally, the robot plays with a human table tennis partner and learns online to improve its behavior.

Creating an AI device that is both easy to control and comfortable to interact with will likely require algorithms for accurately interpreting conversational speech. Homonyms and homophones represent a particular challenge in this regard, thus the study of puns and other forms of humorous wordplay can be informative. Moving beyond the simple resolution of word uncertainty to an understanding of humor is, however, problematic. The Mutual Vulnerability Theory of Laughter identifies numerous variables involved in our differentiating humorous and nonhumorous stimuli. These include available information, type and degree of relationship with others, personal history, culture, and even mood. It also suggests there will be potential liabilities for AI users, retailers, and developers resulting from even successful attempts to identify, respond to, and create humor, as all require the highlighting of vulnerabilities.

Emotional intelligence is the key for acceptance of intelligent agents by humans as equal partners, e.g., in ad hoc teams. At the same time, its existing implementations in intelligent agents are mostly limited to basic affects. Currently, there is no consensus in the understanding of complex and social emotions at the level of functional and computational models. The approach of this work is based on the mental state formalism, originally developed as a part of the cognitive architecture GMU BICA and recently extended to include affective building blocks (A.V. Samsonovich, AAAI Technical Report WS-12-06: 109-116, 2012). In the present work, complex social emotions like humor, jealousy, compassion, shame, pride, etc. are identified as emergent patterns of appraisals represented by schemas, that capture the cognitive nature of these emotions and enable their modeling. A general model of complex emotions and emotional relationships is constructed that can be validated by simulations of emotionally biased interactions and emergent relationships in small groups of agents. The framework will be useful in cognitive architectures for designing human-like-intelligent social agents possessing a sense of humor and other human-like emotionally intelligent capabilities.

Current efforts aim to incorporate knowledge from clinical practice guidelines (CPGs) into computer systems using sophisticated interchange formats. Due to their complexity, such formats require expensive manual formalization work. This paper presents a preliminary study of using natural language processing (NLP) to automatically formalize CPG recommendations. We developed a CPG representation using concepts from the Systematized Nomenclature of Medicine – Clinical Terms (SNOMED–CT), and manually applied this representation to a sample of CPG recommendations that is representative of multiple medical domains and recommendation types. Using this resource, we trained and evaluated a supervised classification model that formalizes new CPG recommendations according to the SNOMED–CT representation, achieving a precision of 75% and recall of 42% (F1 = 54%). We have identified two important lines of future investigation: (1) feature engineering to address the unique linguistic properties of CPG recommendations, and (2) alternative model formulations that are more robust to processing errors. A third line of investigation – creating additional training data for the NLP model – is shown to be of little utility.