Abstract

We present the first shared task on Semantic Textual Relatedness (STR). While earlier shared tasks primarily focused on semantic similarity, we instead investigate the broader phenomenon of semantic relatedness across 14 languages: Afrikaans, Algerian Arabic, Amharic, English, Hausa, Hindi, Indonesian, Kinyarwanda, Marathi, Moroccan Arabic, Modern Standard Arabic, Punjabi, Spanish, and Telugu. These languages originate from five distinct language families and are predominantly spoken in Africa and Asia – regions characterised by the relatively limited availability of NLP resources. Each instance in the datasets is a sentence pair associated with a score that represents the degree of semantic textual relatedness between the two sentences. Participating systems were asked to rank sentence pairs by their closeness in meaning (i.e., their degree of semantic relatedness) in the 14 languages in three main tracks: (a) supervised, (b) unsupervised, and (c) crosslingual. The task attracted 163 participants. We received 70 submissions in total (across all tasks) from 51 different teams, and 38 system description papers. We report on the best-performing systems as well as the most common and the most effective approaches for the three different tracks.

Abstract

The spot size variation due to mechanical jitter is calculated for the Hermite Gaussian (HG) incoherent beam combination system. It is observed that the spot size increases with an increase in mechanical jitter and higher modes HG beams experience less mechanical jitter effect compared to lower mode HG beams.

Abstract

Street lights are ubiquitous public infrastructure in urban areas that can be leveraged for smart city applications. In this paper, we present an electric vehicle charging station (EVCS) that communicates using Wi-SUN network integrated on a network of streetlights, and using oneM2M middleware. The proposed architecture follows the level 2 charging standards and the open charge point protocol (OCPP), ensuring compatibility and interoperability across diverse charging infrastructures. By seamlessly incorporating Wi-SUN network and oneM2M middleware, our architecture enables efficient communication and interaction with a wide array of devices and services. The utilization of the oneM2M platform further enhances the integration by establishing a seamless connection between the EVCS and the broader smart city infrastructure. We have fabricated a proof-of-concept system that consists of the EVCS connected to a Wi-SUN network integrated with the streetlight network in the institute campus. The performance of our solution was evaluated by measuring the latency associated with authentication and billing for EV users. We report the average latency observed over several iterations of charging to be 0.7±0.2 s (excluding the time required for charging). We also measured the Wi-SUN communication range in the campus environment with trees and buildings and found the maximum range to be around 370 m.

Abstract

No Results Found

Abstract

No Results Found

Abstract

This paper presents the myEye2Wheeler dataset, a unique resource of real-world gaze behaviour of two-wheeler drivers navigating complex Indian traffic. Most datasets are from four-wheeler drivers on well-planned roads and homoge- neous traffic. Our dataset offers a critical lens into the unique visual attention patterns and corresponding driving decision- making of Indian two-wheeler drivers. The analysis demon- strates that existing saliency models, like TASED-Net, perform less effectively on the myEye-2Wheeler dataset compared to when applied on the European 4-wheeler eye tracking datasets (DR(Eye)VE), highlighting the need for models specifically tailored to the traffic conditions. By introducing the dataset, we not only fill a significant gap in two-wheeler driver behaviour research in India but also emphasise the critical need for developing context-specific saliency models. The larger aim is to improve road safety for two-wheeler users and lane-planning for this cost-effective mode of transpor

Abstract

Computational History, Trade in Mountain Societies, NLP – NER, Relation Extraction, Application of LLMs.

Abstract

Chemical reaction prediction, encompassing forward synthesis and retrosynthesis, stands as a fundamental challenge in organic synthesis. A widely adopted computational approach frames synthesis prediction as a sequence-to-sequence translation task, using the common SMILES representation for molecules. Current evaluation of machine learning methods for retrosynthesis assume perfect training data, overlooking imperfections in reaction equations in popular datasets, such as missing reactants, products, other physical and practical constraints such as temperature and cost, primarily driven by a focus on the target molecule. This limitation leads to an incomplete representation of viable synthetic routes, especially when multiple sets of reactants can yield a given desired product. In response to these shortcomings, this study examines the prevailing evaluation methods and introduces comprehensive metrics designed to address imperfections in the dataset. Our novel metrics not only assess absolute accuracy by comparing predicted outputs with ground truth but also introduce a nuanced evaluation approach. We provide scores for partial correctness and compute adjusted accuracy through graph matching, acknowledging the inherent complexities of retrosynthetic pathways. Additionally, we explore the impact of small molecular augmentations while preserving chemical properties and employ similarity matching to enhance the assessment of prediction quality. We introduce SynFormer, a sequence-to-sequence model tailored for SMILES representation. It incorporates architectural enhancements to the original transformer, effectively tackling the challenges of chemical reaction prediction. SynFormer achieves a top-1 accuracy of 53.2% on the USPTO-50k dataset, demonstrating an improvement over previous state-of-the-art language models while being more efficient and eliminating the need for pre-training.

Abstract

How can we effectively estimate the quality of translated texts in the medical field, where back-translation is usually available and/or recommended for sensitive documents. This paper proposes a novel metric, GATE 1 , for translation quality estimation task, leveraging the Resource Description Framework (RDF) to encode both semantic and syntactical information of the original and back-translated sentences into RDF graphs. The distance between these graphs is measured to get the semantic similarity score to assess the quality of the translation. Unlike traditional metrics like BLEU and METEOR, our approach is reference-less, capturing both semantic and syntactical information for a comprehensive assessment of translation quality. Our results correlate better with human judgment, giving a better Pearson correlation (0.357) as compared to BLEU (0.200), thereby showing ~70% improvement over BLEU. Our research shows that, in the field of translation evaluation, existing resources like back-translation and RDF could be useful.

Abstract

Manuguru, located in Telangana, India, is a significant coal mining hub in the Godavari Valley Coalfield, with over a century of mining history. The region, experiencing rapid industrialization and urbanization, undergoes comprehensive landscape changes, impacting natural ecosystems, agricultural lands, and water resources beyond the coal-bearing areas. This study presents an analysis of the dynamic land use and land cover (LULC) patterns in Manuguru, utilizing multi-spectral/multi-temporal Landsat satellite imagery from 1987 to 2020. Focused on understanding the impact of mining activities on the region's landscape, advanced band indices, namely, Normalized Difference Vegetation Index( NDVI) and Normalized Difference Water Index(NDWI) are employed alongside visual interpretation techniques helps validate these indices by visually inspecting the actual features on the ground.. The interpretation of Landsat images helped delineate 8 land cover categories: agricultural land, barren land, forest, mining sites, built-up areas, rivers, stagnant water bodies, and dried water bodies. In addition to traditional analysis methods, the study incorporates rate of change calculations and transition matrices to quantify and understand the temporal dynamics of LULC composition. Comparative analysis reveals significant shifts in LULC composition over the study period where the expansion of coal mining activities emerges as a dominant driver of change. This resulted in the loss of ecologically rich forests and the proliferation of overburden hills. Despite the prevalent industrial activities, there is a visible dedication to environmental stewardship by reclaiming overburden dumps through reforestation efforts of open scrub areas. The transition of agricultural lands to built-up areas signifies rapid urban expansion, driven by burgeoning population and economic activities. Similarly, the transformation of water bodies into agricultural lands underscores the human demand for arable land, often at the expense of natural ecosystems. The combined effect of transitions within the land use classes can be attributed to the increase of extractive industries and urbanization.