Abstract

Gauging the knowledge of Pretrained Language Models (PLMs) about facts in niche domains is an important step towards making them better in those domains. In this paper, we aim at evaluating multiple PLMs for their knowledge about world Geography. We contribute (i) a sufficiently sized dataset of masked Geography sentences to probe PLMs on masked token prediction and generation tasks, (ii) benchmark the performance of multiple PLMs on the dataset. We also provide a detailed analysis of the performance of the PLMs on different Geography facts.

Abstract

The emergence of smart grid technology has opened the door for wide-scale automation in decision-making. A distribution company, an integral part of a smart grid system, has to procure electricity from the wholesale market and then sell it to customers in the retail market by publishing attractive tariff contracts. It can deploy autonomous agents to make decisions on its behalf. In this work, we describe the tariff contracts generation strategy of one such autonomous agent, which is based on a Contextual Multi-armed Bandit (ConMAB) based learning technique to generate tariff contracts for various types of customers in the retail market of smart grids. We particularly utilize the Exponential-weight algorithm for Exploration and Exploitation (EXP-3) for ConMAB-based learning. We call our proposed strategy GenerateTariffs-EXP3. Our previous work shows that maintaining an appropriate market share in the retail market yields high net revenue. Thus, we first present a game-theoretic analysis that determines an optimal level of market share. Then we train our proposed strategy to achieve and maintain the suggested level of market share by adapting to the market situation and revising the tariff contracts periodically. We validate our proposed strategy in PowerTAC, a close-to real-world smart grid simulator, and showcase that it is able to maintain the suggested market share.

Abstract

The Multi-Object Navigation (MultiON) task requires a robot to localize an instance (each) of multiple object classes. It is a fundamental task for an assistive robot in a home or a factory. Existing methods for MultiON have viewed this as a direct extension of Object Navigation (ON), the task of localising an instance of one object class, and are pre-sequenced, i.e., the sequence in which the object classes are to be explored is provided in advance. This is a strong limitation in practical applications characterized by dynamic changes. This paper describes a deep reinforcement learning framework for sequence-agnostic MultiON based on an actor-critic architecture and a suitable reward specification. Our framework leverages past experiences and seeks to reward progress toward individual as well as multiple target object classes. We use photo-realistic scenes from the Gibson benchmark dataset in the AI Habitat 3D simulation environment to experimentally show that our method performs better than a pre-sequenced approach and a state of the art ON method extended to MultiON.

Abstract

Speech systems are sensitive to accent variations. This is a challenge in India, which has numerous languages but few linguistic studies on pronunciation variation. The growing number of L2 English speakers reinforces the need to study accents and L1-L2 interactions. We investigate Indian English (IE) accents and report our observations on regional and shared features. Specifically, we observe phonemic variations and phonotactics in speakers’ native languages and apply this to their English pronunciations. We demonstrate the influence of 18 Indian languages on IE by comparing native language features with IE pronunciations obtained from literature studies and phonetically annotated speech. Hence, we validate Indian language influences on IE by justifying pronunciation rules from the perspective of Indian language phonology. We obtain a comprehensive description of generalised and region-specific IE characteristics, which facilitates accent adaptation of existing speech systems.

Abstract

Cocaine use disorder (CUD) is described as a compulsive urge to seek and consume cocaine despite the inimical consequences. MRI studies from different modalities have shown that CUD patients exhibit structural and/or functional connectivity pathology among several brain regions. Nevertheless, both connectivities are commonly studied and analyzed separately, which may potentially obscure its relationship between them, and with the clinical pathology. Here, we compare and contrast structural and functional brain networks in CUD patients and healthy controls (HC) using multimodal fusion. The sample consisted of 63 (8 females) CUD patients and 42 (9 females) healthy controls (HC), recruited as part of the SUDMEX CONN database. For this, we computed a battery of graph-based measures from multi-shell diffusion-weighted imaging and resting state fc-fMRI to quantify local and global connectivity. Then we used multimodal canonical component analysis plus joint independent component analysis (mCCA+jICA) to compare between techniques, and evaluate group differences and its association with clinical alteration. Unimodal results showed a striatal decrease in the participation coefficient, but applied supervised data fusion revealed other regions with cocaine-related alterations in joint functional communication. When performing multimodal fusion analysis, we observed a higher centrality of the interrelationship and a lower participation coefficient in patients with CUD. In contrast to the unimodal approach, the multimodal fusion method was able to reveal latent information about brain regions involved in impairment due to cocaine abuse. The present results could help in understanding the pathology of CUD in order to develop better pre-treatment/post-treatment intervention designs

Abstract

Embodiments herein provide a system and method for automatically generating a sign language video from an input speech using the machine learning model. The method includes (i) extracting a plurality of spectrograms of an input speech by (a) encoding, using an encoder, a time domain series of the input speech to a frequency domain series, and (b) decoding, using a decoder, a plurality of tokens for time steps of the frequency domain series, (ii) generating a plurality of pose sequences for a current time step of the plurality of spectrograms using a first machine learning model, and (iii) automatically generating, using a discriminator of a second machine learning model, a sign language video for the input speech using the plurality of pose sequences and the plurality of spectrograms when the plurality of pose sequences are matched with corresponding the plurality of spectrograms that are extracted.

Abstract

The advances in Artificial Intelligence are creating new opportunities to improve people’s lives around the world, from business to healthcare, from lifestyle to education. For example, some systems profile the users using their demographic and behavioral characteristics to make certain domain-specific predictions. Often, such predictions impact the user’s life directly or indirectly (e.g., loan disbursement, determining insurance coverage, shortlisting applications, etc.). As a result, the concerns over such AI-enabled systems are also increasing. To address these concerns, such systems are mandated to be responsible: transparent, fair, and explainable to developers and end-users. In this paper, we present ComplAI, a unique framework to enable, observe, analyze and quantify explainability, robustness, performance, fairness, and model’s behavior in drift scenarios, and to provide a single Trust Factor that evaluates different supervised Machine Learning models not just from their ability to make correct predictions but from overall responsibility perspective. The framework helps users to (a) connect their models and enable explanations, (b) assess and visualize different aspects of the model such as robustness, drift susceptibility, and fairness, and (c) compare different models (from different model families or obtained through different hyperparameter settings) from an overall perspective thereby facilitating actionable recourse for improvement of the models. ComplAI is model agnostic and works with different supervised machine learning scenarios (i.e., Binary Classification, Multi-class Classification, and Regression) and frameworks (viz. scikit-learn, TensorFlow, etc.). It can be seamlessly integrated with any ML life-cycle framework. Thus, this already deployed framework aims to unify critical aspects of Responsible AI systems for regulating the development process of such real systems. The poster paper of ComplAI is also available

Abstract

Developing methods for extracting relevant legal information to aid legal practitioners is an active research area. In this regard, research efforts are being made by leveraging different kinds of information, such as meta-data, citations, keywords, sentences, paragraphs, etc. Similar to any text document, legal documents are composed of paragraphs. In this paper, we have analyzed the resourcefulness of paragraph-level information in capturing similarity among judgments for improving the performance of precedence retrieval. We found that the paragraph-level methods could capture the similarity among the judgments with only a few paragraph interactions and exhibit more discriminating power over the baseline document-level method. Moreover, the comparison results on two benchmark datasets for the precedence retrieval on the Indian supreme court judgments task show that the paragraph-level methods exhibit comparable performance with the state-of-the-art methods.

Abstract

This paper focuses on optimal beamforming to maximize the mean signal-to-noise ratio (SNR) for a passive reconfigurable intelligent surface (RIS)-aided multiple-input single-output (MISO) downlink system. We consider a realistic setting where both the direct and indirect (through RIS) links to the user equipment (UE) experience correlated Rician fading. Such a general fading model is particularly important to capture the impact of line-of-sight (LoS) and correlated multipath fading that may occur due to the compact placement of a large number of RIS elements. The assumption of passive RIS imposes the unit modulus constraint, which makes the beamforming problem non-convex. To tackle this issue, we apply semidefinite relaxation (SDR) to obtain the optimal phase-shift matrix and propose an iterative algorithm to obtain a statistically optimal solution for the transmit beamforming vector and RIS-phase shift matrix. Further, to measure the performance of the proposed beamforming scheme, we analyze key system performance metrics such as outage probability (OP) and ergodic capacity (EC). Similar to the existing works, the OP and EC evaluations rely on the numerical computation of the proposed iterative algorithm. However, this is not conducive to revealing the functional dependence of system performance on key parameters such as line-of-sight (LoS) components, correlated fading, number of reflecting elements, number of antennas at the base station (BS), and fading factor. To overcome this major limitation, we derive closed-form expressions for the optimal beamforming vector and phase shift matrix for various special cases of the above general fading model. These fixed-point solutions aid in deriving a closed-form solution for OP that further provides a direct evaluation of EC. These mathematical expressions are then used to gain useful insights into the system’s performance. We analytically establish the fact that correlated fading is more beneficial than the independent and identically distributed (i.i.d.) case when the LoS components are blocked. Further, we also analytically demonstrate that the maximum mean SNR improves linearly/quadratically with the number of RIS elements in the absence/presence of LoS component under i.i.d. fading.

Abstract

Brain stroke has become a significant burden on global health and thus we need remedies and prevention strategies to overcome this challenge. For this, the immediate identification of stroke and risk stratification is the primary task for clinicians. To aid expert clinicians, automated segmentation models are crucial. In this work, we consider the publicly available dataset ATLAS v2.0 to benchmark various end-to-end supervised U-Net style models. Specifically, we have benchmarked models on both 2D and 3D brain images and evaluated them using standard metrics. We have achieved the highest Dice score of 0.583 on the 2D transformer-based model and 0.504 on the 3D residual U-Net respectively. We have conducted the Wilcoxon test for 3D models to correlate the relationship between predicted and actual stroke volume.