Machine reading aims at extracting formal knowledge representations from text to enable programs to execute some performance task, for example, diagnosis or answering complex queries stated in a formal representation language. Information extraction techniques are a natural starting point for machine reading, however, since they focus on explicit surface features at the phrase and sentence level, they generally miss information only stated implicitly. Moreover, the combination of multiple extraction results leads to error compounding which dramatically affects extraction quality for composite structures. To address these shortcomings, we present a new approach which aggregates locally extracted information into a larger story context and uses abductive constraint reasoning to generate the best story-level interpretation. We demonstrate that this approach significantly improves formal question answering performance on complex questions.

Chairs and committees of the FLAIRS-25 conference.

Depression and other mood disorders are common and disabling disorders. We present work towards an objective diagnostic aid supporting clinicians using affective sensing technology with a focus on acoustic and statistical features from spontaneous speech. This work investigates differences in expressing positive and negative emotions in depressed and healthy control subjects as well as whether initial gender classification increases the recognition rate. To this end, spontaneous speech from interviews of 30 subjects of each depressed and controls was analysed, with a focus on questions eliciting positive and negative emotions. Using HMMs with GMMs for classification with 30-fold cross-validation, we found that MFCC, energy and intensity features gave highest recognition rates when female and male subjects were analysed together. When the dataset was first split by gender, log energy and shimmer features, respectively, were found to give the highest recognition rates in females, while it was loudness for males. Overall, correct recognition rates from acoustic features for depressed female subjects were higher than for male subjects. Using statistical features, we found that the response time and average syllable duration were longer in depressed subjects, while the interaction involvement and articulation rate were higher in control subjects.

In NL2OCL project, we aim to translate English specification of constraints to formal constraints such as OCL (Object Constraint Language). In English to OCL translation, our contribution is a semantic analyzer that uses the output of the Stanford parser for shallow and deep semantic parsing. Our analysis of the output of shallow semantic parsing showed that semantic roles were mis-identified for a few English constraints due to semantic ambiguity. Similarly, in deep semantic parsing, it is difficult to resolve scope of quantifier operators due to scope ambiguity that is another sub-type of semantic ambiguity. In this paper, we highlight the identified cases of semantic ambiguities in English constraints. We also present a novel approach to automatically resolve the identified cases of the semantic ambiguities. The presented approach is also evaluated to show that by addressing the identified cases of semantic ambiguities, we can generate more accurate and complete formal (OCL) specifications.

We propose and give a preliminary test of a new metric for the quality of the commonsense knowledge and reasoning of large AI databases: Using the same measurement as is used for a four-year-old, namely, an IQ test for young children. We report on results obtained us- ing test questions we wrote in the spirit of the questions of the Wechsler Preschool and Primary Scale of Intelligence, Third Edition (WPPSI-III) on the ConceptNet system, which were, on the whole, quite strong.

Applicative languages (Church’s ?-calculus and Curry’s combinatory Logic) and functional types are useful logical tools for studying and representing the meanings of verbal predicates and other linguistic operators (prepositions, preverbs …) of natural languages by means of combinations of abstract and cultural primitives. The situations are semantic expressions associated to sentences; they are written by means of applicative expressions (ae) generated from semantic abstract primitives: (i) cognitive basic types (individual, massive, distributive class, abstract places, activity, situations…); (ii) operators transforming assigned types (as topological operators : take the interior, exterior, boundary, closure of an abstract place); (iii) kinematic, dynamic, cause relators:  MOVT and CHANG expressing movement or change the state of an entity; FAIRE, CONTR (to control) and TELEO (to intend a teleonomic situation) introducing a link between a kinematic situation and an entity (agent, intermediary instrument…); CAUSE establishing a link between two different situations (a cause and an effect). These abstract primitives are interpreted inside of the cognitive fields of perception and action. They are sources of numerous grammaticalizations in languages. Verbal predicates involve an actualization over topological intervals of instants; thus, it is necessary to introduce complex operators for transforming a situation into an aspectual situation (state, event, process …). This article presents systematically these abstract primitives with some examples of meanings represented inside the applicative framework. The applicative expressions of situations (semantic schemes) defined to a semantic level can be integrated into lexical predicates of another level, by using combinators of combinatory logic; this integration process in Cognitive and Applicative Grammar (GAC) has already been presented (in precedent FLAIRS).

In this paper we describe ongoing undergraduate research projects that allow us to shift emphasis from teaching to a more active form of student participation. More specifically our projects are on automatic gesture recognition using the Kinect 3D sensor from Microsoft Research and machine learning systems. We have observed the following benefits for our undergraduate students: learning a topic area in AI relatively early; developing proficiency in laboratory practice, specifically, systematic data collection and programming on multiple platforms; learning to use appropriate methodology; applying knowledge to a real situation; learning to analyze data and transform it to various representations; appreciation of scientific experiments and learning what scientific research actually entails.

Are the words that people use indicative of their personality type preferences? In this paper, it is hypothesized that word-usage is not independent of personality type, as measured by the Myers-Briggs Type Indicator (MBTI) personality assessment tool. In-class writing samples were taken from 40 graduate students along with the MBTI. The experiment utilizes naïve Bayes classifiers and Support Vector Machines (SVMs) in an attempt to guess an individual’s personality type based on their word-choice. Classification is also attempted using emotional, social, cognitive, and psychological dimensions elicited by the analysis software, Linguistic Inquiry and Word Count (LIWC). The classifiers are evaluated with 40 distinct trials (leave-one-out cross validation), and parameters are chosen using leave-one-out cross validation of each trial’s training set. The experiment showed that the naïve Bayes classifiers (word-based and LIWC-based) outperformed the SVMs when guessing Sensing-Intuition (S-N) and Thinking-Feeling (T-F).

Using natural language as a way for students to interact with an ITS has many advantages. However, creating the intelligence with which the tutor evaluates a student’s natural language input is challenging. We describe a system, ConceptGrid, that allows non-programmers to create the instruction for checking natural language input. Three tutor authors used the system to develop answer templates for conceptual-based questions in statistics. Results indicate ConceptGrid is a viable system for non-programmers to use to allow students to use natural language to interact with a tutor.

This work discusses the problem of sparse signal recovery when there is correlation among the values of non-zero entries. We examine intra-vector correlation in the context of the block sparse model and inter-vector correlation in the context of the multiple measurement vector model, as well as their combination. Algorithms based on the sparse Bayesian learning are presented and the benefits of incorporating correlation at the algorithm level are discussed. The impact of correlation on the limits of support recovery is also discussed highlighting the different impact intra-vector and inter-vector correlations have on such limits.