Abstract

In this paper, we propose a novel two-step technique for text classification using autoregressive Language Models (LM). In the first step, a set of perplexity and log-likelihood based numeric features are elicited from an LM for a text instance to be classified. Then, in the second step, a classifier based on these features is trained to predict the final label. The classifier used is usually a simple machine learning classifier like Support Vector Machine (SVM) or Logistic Regression (LR) and it is trained using a small set of training examples. We believe, our technique presents a whole new way of exploiting the available training instances, in addition to the existing ways like fine-tuning LMs or in-context learning. Our approach stands out by eliminating the need for parameter updates in LMs, as required in fine-tuning, and does not impose limitations on the number of training examples faced while building prompts for in-context learning. We evaluate our technique across 5 different datasets and compare with multiple competent baselines.

Abstract

To employ Pre-trained Language Models (PLMs) as knowledge containers in niche domains it is important to gauge the knowledge of these PLMs about facts in these domains. It is also an important pre-requisite to know how much enrichment effort is required to make them better. As part of this work, we aim to gauge and enrich small PLMs for knowledge of world geography. Firstly, we develop a moderately sized dataset of masked sentences covering 24 different fact types about world geography to estimate knowledge of PLMs on these facts. We hypothesize that for this niche domain, smaller PLMs may not be well equipped. Secondly, we enrich PLMs with this knowledge through fine-tuning and check if the knowledge in the dataset is infused sufficiently. We further hypothesize that linguistic variability in the manual templates used to embed the knowledge in masked sentences does not affect the knowledge infusion. Finally, we demonstrate the application of PLMs to tourism blog search and Wikidata KB augmentation. In both applications, we aim at showing the effectiveness of using PLMs to achieve competitive performance.

Abstract

The intricate link between brain textbf{Functional Connectivity (FC)} and textbf{Structural Connectivity (SC)} is explored through models performing diffusion on SC to derive FC, using varied methodologies from single to multiple textbf{Graph Diffusion Kernels}. However, existing studies have not correlated diffusion scales with specific brain Regions of Interest (RoIs), limiting the applicability of graph diffusion. We propose a novel approach using textbf{Graph Diffusion Wavelets} to learn the appropriate diffusion scale for each RoI to accurately estimate the SC-FC mapping. Using the open Human Connectome Project (HCP) dataset, we achieve an average textbf{Pearson's correlation} value of 0.833, surpassing the state-of-the-art methods for prediction of FC. It is important to note that the proposed architecture is entirely linear, computationally efficient, and notably demonstrates the textbf{power-law} distribution of diffusion scales. Our results show that the bilateral frontal pole, by virtue of it having large diffusion scale, forms a large community structure. The finding is in line with the current literature on the role of the frontal pole in resting-state networks. Overall, the results underscore the potential of graph diffusion wavelet framework for understanding how the brain structure leads to functional connectivity.

Abstract

The concept of raga in Indian classical music serves as a complex, multifaceted melodic entity that can be approached through various perspectives. Compositions within a raga act as foundational structures, serving as the bedrock for improvisations. Analyzing their textual notations is easier and more objective in comparison with analyzing audio samples. A significant amount of musical insights can be derived from the discrete swara sequences alone. This paper aims to construct an intuitive visualization of raga space, using swara sequences from raga compositions. Notations from public sources are normalized, and their TF-IDF features are projected into a low-dimensional space. This approach allows for qualitative analysis of both Carnatic and Hindustani ragas, mapping them to known raga theory.

Abstract

Edge–cloud coordination offers the chance to mitigate the enormous storage and processing load brought on by a massive increase in traffic at the network’s edge. Though this paradigm has benefits on a large scale, outsourcing the sensitive data from the smart devices deployed in an Internet of Things (IoT) application may lead to privacy leakage. With an attribute-based keyword search (ABKS), the search over ciphertext can be achieved; this reduces the risk of sensitive data explosion. However, ABKS has several issues, like huge computational overhead to perform multi-keyword searches and tracing malicious users. To address these issues and enhance the performance of ABKS, we propose a novel traceable and lightweight attribute-based keyword search technique in an Edge–cloud-assisted IoT, named TL-ABKS, using edge–cloud coordination. With TL-ABKS, it is possible to do effective multi-keyword searches and implement fine-grained access control. Further, TL-ABKS outsources the encryption and decryption computation to edge nodes to enable its usage to resource-limited IoT smart devices. In addition, TL-ABKS achieves tracing user identity who misuse their secret keys. TL-ABKS is secure against modified secret keys, chosen plaintext, and chosen keyword attacks. By comparing the proposed TL-ABKS with the current state-of-the-art schemes, and conducting a theoretical and experimental evaluation of its performance and credibility, TL-ABKS is efficient.

Abstract

Voltage-Controlled Oscillator (VCO) is a crucial component of a Phase-Locked Loop (PLL) system. However, the frequency of a typical Ring-Oscillator-based VCO varies by about 2–3 times across its frequency tuning range and process, voltage and temperature (PVT) conditions. The gain of a Ring-VCO is another crucial parameter that is significantly affected by PVT variations, thereby impacting the stability and loop bandwidth of the PLL. This paper describes a compensation technique to minimize variations in Ring-VCO gain across PVT conditions. A Charge-Pump PLL operating at 4 GHz is implemented in a 28nm CMOS process. The gain of the Ring-VCO varies by ±27% across PVT at 4 GHz. This gain variation of Ring-VCO combined with other PVT-dependent blocks of PLL lead to a deviation of ±60% in Loop Bandwidth and ±21 % in Phase-Margin (PM). Process trimming reduces the VCO gain variation to ±25 %. Subsequently, the temperature compensation technique reduces the VCO gain variation by 3 times to ±8 %, over a temperature range −40∘C to 125∘C . The resulting variations in Loop Bandwidth and Phase-Margin are reduced to ±34%” and ±l5%” respectively.

Abstract

In this work, we introduce an innovative approach to estimate the vital signs of multiple human subjects simultaneously in a non-contact way using a Frequency Modulated Continuous Wave (FMCW) radar-based system. Traditional vital sign monitoring methods often face significant limitations, including subject discomfort with wearable devices, challenges in calibration, and the risk of infection transmission through contact measurement devices. To address these issues, this research is motivated by the need for versatile, non-contact vital monitoring solutions applicable in various critical scenarios. This work also explores the challenges of extending this capability to an arbitrary number of subjects, including hardware and theoretical limitations. Supported by rigorous experimental results and discussions, the paper illustrates the system’s potential to redefine vital sign monitoring. An FPGA-based implementation is also presented as proof of concept for a hardware-based and portable solution, improving upon previous works by offering 2.7x faster execution and 18.4% less Look-Up Table (LUT) utilization, as well as providing over 7400x acceleration compared to its software counterpart.

Abstract

Addressing blockchain's insufficient throughput and scalability is imperative for practical viability. Off-chain approaches, such as state channels (including Hash Time Lock Contract (HTLC), virtual channels), demonstrate enhanced throughput by enabling parallel transaction processing. While virtual channels introduce execution complexity, HTLC suffers from high update delays. Moreover, existing methods face network attacks. We present Sharding-based Hybrid State Channel (SharHSC) to address these issues. Firstly, we introduce a novel off-chain sharding architecture, which partitions proxy nodes into multiple shards. Thus, when the off-chain node count increases, adding shards enhances system throughput. Secondly, each shard establishes a supervisory committee to record latest channel statuses to ensure accurate fund distribution upon channel closure. Thirdly, we combine the strengths of HTLC and virtual channels. In particular, SharHSC constructs a single virtual channel across all the nodes involved in the payment by treating the nodes between payer and payee as an intermediate entity, which utilizes HTLC for fund routing. This realizes both low latency and streamlined complexity. Finally, our work is substantiated by security analysis and experiments. As the node number varies, compared with HTLC and virtual channels, the latency is reduced by 49.32% and 31.82%, and the throughput is increased by 8.93 and 1.89 times.

Abstract

The widespread adoption of Large Language Models (LLMs) and awareness around multilingual LLMs have raised concerns regarding the potential risks and repercussions linked to the misapplication of AI-generated text, necessitating increased vigilance. While these models are primarily trained for English, their extensive training on vast datasets covering almost the entire web, equips them with capabilities to perform well in numerous other languages. AI-Generated Text Detection (AGTD) has emerged as a topic that has already received immediate attention in research, with some initial methods having been proposed, soon followed by the emergence of techniques to bypass detection. In this paper, we report our investigation on AGTD for an indic language Hindi. Our major contributions are in four folds: i) examined 26 LLMs to evaluate their proficiency in generating Hindi text, ii) introducing the AI-generated news article in Hindi (AG_hi) dataset, iii) evaluated the effectiveness of five recently proposed AGTD techniques: ConDA, J-Guard, RADAR, RAIDAR and Intrinsic Dimension Estimation for detecting AI-generated Hindi text, iv) proposed Hindi AI Detectability Index (ADI_hi) which shows a spectrum to understand the evolving landscape of eloquence of AI-generated text in Hindi. The code and dataset is available at https://github.com/ishank31/Counter_Turing_Test

Abstract

The objective of the MTIL track in FIRE 2023 was to encourage the development of Indian Language to Indian Language (IL-IL) Neural Machine Translation models. The languages covered in the track included Hindi, Gujarati, Kannada, Odia, Punjabi, Urdu, Telugu, Kashmiri, and Sindhi. The track consists of two tasks: (i) a General Translation Task and (ii) a Domain specific Translation Task with Governance and Healthcare being the chosen domains. For the listed languages, we proposed 12 diverse language directions for the general domain translation task and 8 each for healthcare and governance domains. Participants were encouraged to submit models for one or more language pairs. We witnessed the creation of 34 distinct models spanning various language pairs and domains. Model assessments were conducted using five evaluation metrics: BLEU, CHRF, CHRF++, TER, and COMET. The submitted model outputs were ranked based on the CHRF score.