We examine the ability of a genetic algorithm to learn a predictive model that can estimate the likelihood that a physical therapist will receive annual Medicare payments above or below the industry median based on the physical therapist's practice parameters. We compare the performance of a canonical genetic algorithm and a self adaptive genetic algorithm with the performance of traditional logistic regression. Results show that both genetic algorithm approaches are competitive with logistic regression with the canonical genetic algorithm consistently outperforming logistic regression.

The Preferences for Everyday Living Inventory (PELI) is a 72-question instrument used for helping nursing homes assess person-centered care. In particular, the approach allows residents to express their preferences for both care and activities in order to provide direct care workers with insights on how to best provide a high-quality living experience. Among the challenges of using the PELI is its length: 72 questions give rise to issues of survey fatigue while also creating a workflow bottleneck for those providing care. In this paper we explore and evaluate the use of three different recommender strategies that we have applied to the PELI. In particular, we present the use of both rule-based and neighborhood-based collaborative filtering in order to make recommendations on which preference questions to present to a resident. We illustrate the approaches by providing a domain-specific example, and then compare the approaches across a number of performance and quality metrics.

Video games have proved to be a very defying laboratory to study machine-learning techniques, such as Deep Reinforcement Learning (DRL) algorithms. This paper presents a new approach for a DRL-based agent trained through Deep Q-Network (DQN) technique to perform free kicks in FIFA 18 game. The main motivation for choosing this case study is the fact that, like in many situations of the real life, FIFA represents a stochastic environment. Coping with this task, the main contributions of the present paper consist on: inspired on the OpenAI Gym and on the OpenAI Universe platforms, implementing a new user-friendly interface (in terms of portability and use simplicity) to connect the learning module with the 3D FIFA's game environment; implementing a DRL-based agent for free kicks in FIFA that uses two distinct data representations retrieved from lower cost computational procedures. The results were validated through two evaluative parameters: score of well succeed kicks and training time.

Development of interesting and complex characters is the most important element of a narrative. Presented in this work is fAIble II, an automated narrative generation system that focuses on character development. fAIble II leverages a graph database, containerized modules, knowledge templates, and language structuring to produce diverse and coherent stories. Story progression is driven by character perception, emotion, personality, and interaction with the story world. The resultant system has been tested via anonymous questionnaire. Responses suggest its ability to create diverse, sensible narratives using character development.

Analysis of spontaneous speech is an important tool for clinical linguists to diagnose various dementia types that affect the language processing areas. Prosody is affected by some dementia types, most notably Parkinson's disease (PD, degradation of voice quality, unstable pitch), Alzheimer's disease (AD, monotonic pitch), and the non-fluent type of Primary Progressive Aphasia (PPA-NF, hesitant, non-fluent speech). Prosodic features can be computed efficiently by software. In this study, we evaluate the performance of a SVM classifier that is trained on prosodic features only. The limitation to only prosody yields baseline results that can be used in a later stage to evaluate the added effect of variables of (morpho) syntax. The goal is to distinguish different dementia types based on the recorded speech. Results show that the classifier can distinguish some dementia types (PPA-NF, AD), but not others (PD, PPA-SD).

English uses the passive voice more frequently than French. One method of translating the passive includes rendering the sentence as active by using an active verb, and changing the placement of the verb’s arguments. We are studying extra-syntactic features that predict where this method of translating the passive voice is used, in-cluding animacy and information status. We have obtained data from examining the Hansard, the transactions of the Canadian Parliament, which is published in both languages. This paper presents the results of a small mechanized corpus analysis on the relevance of the relative animacy of the agent (or experiencer) and the theme. This information will help to achieve desired stylistic output in a bilingual surface realizer.

Multi-party linguistic entrainment refers to the phenomenon that speakers tend to speak more similarly during conversation. We first developed new measures of multi-party entrainment on features describing linguistic style, and then examined the relationship between entrainment and team characteristics in terms of gender composition, team size, and diversity. Next, we predicted the perception of team social outcomes using multi-party linguistic entrainment and team characteristics with a hierarchical regression model. We found that teams with greater gender diversity had higher minimum convergence than teams with less gender diversity. Entrainment contributed significantly to predicting perceived team social outcomes both alone and controlling for team characteristics.

Dialogue systems intend to facilitate the interaction between humans and computers. A key element in a dialogue system is the conceptual model which represents a domain. Folksonomies are very simple forms of knowledge representation which may be used to specify the conceptual model. However, folksonomies suffer by nature from issues related to ambiguity. In this paper, we present a method which uses linguistic context for learning folksonomies from task-oriented dialogues. The linguistic context can be useful for reducing ambiguity, for instance, when using the folksonomies for interpreting utterances. Experiments show that the learned folksonomies increase the accuracy of the interpretation compared when not using the contextual information.

Automatically identifying implicit discourse relations requires an in-depth semantic understanding of the text fragments involved in such relations. While early work investigated the usefulness of different classes of input features, current state-of-the-art models mostly rely on standard pre-trained word embeddings to model the arguments of a discourse relation. In this paper, we introduce a method to compute contextualized representations of words, leveraging information from the sentence dependency parse, to improve argument representation. The resulting token embeddings encode the structure of the sentence from a dependency point of view in their representations. Experimental results show that the proposed representations achieve state-of-the-art results when input to standard neural network architectures, surpassing complex models that use additional data and consider the interaction between arguments.

We propose a concept map based approach to assessing freely generated student responses. The proposed approach is based on a novel automated tuple extraction system, DT-OpenIE, for automatically extracting concept maps from student responses. The DT-OpenIE system is significantly better in terms of concept map quality for assessment purposes than state-of-the-art open information extraction (IE) systems such as Ollie or Stanford as evidenced by our experimental results. The concept map based approach can significantly improve tracking student's mastery level in an automated tutoring environment such as DeepTutor where students interact with the automated tutor using natural language because the concept maps can be used not only to generate a holistic score assessing the accuracy of a student response but also enable diagnostic feedback.