Abstract

Within the social system of science, citation practices characterize social functions like the conferral of recognition upon the work of others as well as the acknowledgement of one’s intellectual debt. However, the structure of intellectual influence is misrepresented when only the immediate citations and their cardinality are taken into consideration. Thus, in order to better understand the associative dissemination of influence and approximately construe the anatomy of this structure, complex interactions in the convoluted network of authors and papers need to be probed. Our study aims at understanding these heterogeneous complex interactions. For the bibliographic dataset of authors and publications, we define proxy scores that attempt to determine the associative influence of the cited author over the citing author. In order to harness structural connectivity of the network, we generate author vector representations using these influence scores. Furthermore, with a view to assess the competence of our proposed scores, we evaluate these representations and provide an empirical study of the results obtained with our algorithm against the baseline and also present a qualitative analysis.

Abstract

The brain is the most complex biological system that exists. Timbre, in its very nature, is a multidimensional concept with several levels of abstraction thus rendering the investigation of its processing in the brain extremely challenging. Timbre processing can be discussed in relation to levels of abstraction. Low- to midlevel representations can be associated with the neural representation of acoustic structure while high-level abstractions correspond to the neural representation of sound source properties. Furthermore, neural correlates of timbre can be broadly classified based on three stimulus categories, that is, those pertaining to music, speech, and environmental sounds. This chapter summarizes studies that have attempted to uncover neural correlates of varying levels of timbre abstractions. Finally, developments in methodological approaches are described, including the shift from univariate to multivariate statistical models, the employment of more naturalistic stimuli, and brain measurement paradigms from hitherto controlled auditory paradigms.

Abstract

Owing to the stigmatization of mental illnesses such as depression in India [1], there is a need for indirect unsuspecting ways to identify risk for depression and provide timely intervention. Healthy-Unhealthy Music scale (HUMS) [2] is one such assessment tool developed on Australian population that uses music engagement as an indicator of anxiety levels and potential high-risk for depression as assessed by Kessler’s Psychological Distress Scale (K10). The current study aims to ascertain its validity in an Indian setting followed by applying machine learning approaches to predict mental well-being from music associations. A diverse group comprising Indian adult population was assessed using HUMS and mental well-being and proneness to depression measures. HUMS structure investigated via Exploratory factor analyses, and concurrent validity tested with correlations to depression risk and wellbeing revealed high external validity and applicability of HUMS in Indian adult population.Furthermore, very low in-sample error for models like Support Vector Machines (SVM) with nonlinear kernels suggests an underlying pattern between HUMS responses and K10 score. Finally, a two-class model resulted in out of sample accuracy of 81%. To conclude, HUMS demonstrates high generalizability and hence applicability in Indian adult population and potential for employing ML models to capture the underlying pattern.

Abstract

Musical training causes structural and functional changes in the brain due to its sensory-motor demands, but the modulatory effect of musical training on music feature processing in the brain in a continuous music listening paradigm, has not been investigated thus far. In this work, we investigate the differences between musicians and non-musicians in the encoding of musical features encompassing musical timbre, rhythm and tone. 18 musicians and 18 non-musicians were scanned using fMRI while listening to 3 varied stimuli. Acoustic features corresponding to timbre, rhythm and tone were computationally extracted from the stimuli and correlated with brain responses, followed by t-tests on group level maps to uncover encoding differences between the two groups. The musicians demonstrated greater involvement of limbic and reward regions, and regions possessing adaptations to music processing due to training, indicating greater analytic processing. However, as a group, they did not exhibit large regions of consistent correlation patterns, especially in processing high-level features, due to differences in processing strategies arising out of their varied training. The non-musicians exhibited broader regions of correlations, implying greater similarities in bottom-up sensory processing.

Abstract

Keeping time is fundamental for our everyday existence. Various isochronous activities, such as locomotion, require us to use internal timekeeping. This phenomenon comes into play also in other human pursuits such as dance and music. When listening to music, we spontaneously perceive and predict its beat. The process of beat perception comprises both beat inference and beat maintenance, their relative importance depending on the salience of beat in the music. To study functional connectivity associated with these processes in a naturalistic situation, we used functional magnetic resonance imaging to measure brain responses of participants while they were listening to a piece of music containing strong contrasts in beat salience. Subsequently, we utilized dynamic graph analysis and psychophysiological interactions (PPI) analysis in connection with computational modelling of beat salience to investigate how functional connectivity manifests these processes. As the main effect, correlation analyses between the obtained dynamic graph measures and the beat salience measure revealed increased centrality in auditory-motor cortices, cerebellum, and extrastriate visual areas during low beat salience, whereas regions of the default mode- and central executive networks displayed high centrality during high beat salience. PPI analyses revealed partial dissociation of functional networks belonging to this pathway indicating complementary neural mechanisms crucial in beat inference and maintenance, processes pivotal for extracting and predicting temporal regularities in our environment.

Abstract

Variational autoencoders were proven successful in domains such as computer vision and speech processing. Their adoption for modeling user preferences is still unexplored, although recently it is starting to gain attention in the current literature. In this work, we propose a model which extends variational autoencoders by exploiting the rich information present in the past preference history. We introduce a recurrent version of the VAE, where instead of passing a subset of the whole history regardless of temporal dependencies, we rather pass the consumption sequence subset through a recurrent neural network. At each time-step of the RNN, the sequence is fed through a series of fully-connected layers, the output of which models the probability distribution of the most likely future preferences. We show that handling temporal information is crucial for improving the accuracy of the VAE: In fact, our model beats the current state-of-the-art by valuable margins because of its ability to capture temporal dependencies among the user-consumption sequence using the recurrent encoder still keeping the fundamentals of variational autoencoders intact.

Abstract

Clustering has become a very popular machine learning technique for identifying groups of data points with common features in a set of data points. In several applications, there is a need to explain the clusters so that the user can understand the underlying commonalities. One such application is in the area of building energy simulation. There is a need to cluster solutions obtained by parametric energy simulation runs and explain the characteristics of each cluster for human consumption. This paper demonstrates how the axis-aligned hyper-rectangles based clustering, on building energy simulation data, can help identify clusters and describe the governing rules for each cluster. We are calling these rules design strategies. Instead of the distance-based clustering methods that are unable to extract simple rules from the underlying commonalities in each cluster, this method is able to overcome this limitation. This method is applied to identify design strategies from a parametric run of a simple five-zone rectangular building model. Based on a user-given threshold, low energy solutions are selected for clustering. Each axis-aligned hyper-rectangle cluster is a unique design strategy that can be easily communicated to the user.

Abstract

As scientific communities grow and evolve, there is a high demand for improved methods for finding relevant papers, comparing papers on similar topics and studying trends in the research community. All these tasks involve the common problem of extracting structured information from scientific articles. In this paper, we propose a novel, scalable, semi-supervised method for extracting relevant structured information from the vast available raw scientific literature. We extract the fundamental concepts of “aim”,” method” and “result” from scientific articles and use them to construct a knowledge graph. Our algorithm makes use of domain-based word embedding and the bootstrap framework. Our experiments show that our system achieves precision and recall comparable to the state of the art. We also show the domain independence of our algorithm by analyzing the research trends of two distinct communities-computational linguistics and computer vision.

Abstract

This paper describes our system (Fermi) for Task 6: OffensEval: Identifying and Categorizing Offensive Language in Social Media of SemEval-2019. We participated in all the three sub-tasks within Task 6. We evaluate multiple sentence embeddings in conjunction with various supervised machine learning algorithms and evaluate the performance of simple yet effective embedding-ML combination algorithms. Our team Fermi’s model achieved an F1-score of 64.40%, 62.00% and 62.60% for sub-task A, B and C respectively on the official leaderboard. Our model for sub-task C which uses pre-trained ELMo embeddings for transforming the input and uses SVM (RBF kernel) for training, scored third position on the official leaderboard. Through the paper we provide a detailed description of the approach, as well as the results obtained for the task.

Abstract

This paper describes our system (Fermi) for Task 5 of SemEval-2019: HatEval: Multilingual Detection of Hate Speech Against Immigrants and Women on Twitter. We participated in the subtask A for English and ranked first in the evaluation on the test set. We evaluate the quality of multiple sentence embeddings and explore multiple training models to evaluate the performance of simple yet effective embedding-ML combination algorithms. Our team-Fermi’s model achieved an accuracy of 65.00% for English language in task A. Our models, which use pretrained Universal Encoder sentence embeddings for transforming the input and SVM (with RBF kernel) for classification, scored first position (among 68) in the leaderboard on the test set for Subtask A in English language. In this paper we provide a detailed description of the approach, as well as the results obtained in the task.