arXiv subjects

Nikhil Arora

Publications and source records attributed to Nikhil Arora.

21 records · Page 2Linked to original sources

arXiv2020

On-Device Sentence Similarity for SMS Dataset

Determining the sentence similarity between Short Message Service (SMS) texts/sentences plays a significant role in mobile device industry. Gauging the similarity between SMS data is thus necessary for various applications like enhanced searching and navigation, clubbing together SMS of similar type when given a custom label or tag is provided by user irrespective of their sender etc. The problem faced with SMS data is its incomplete structure and grammatical inconsistencies. In this paper, we propose a unique pipeline for evaluating the text similarity between SMS texts. We use Part of Speech (POS) model for keyword extraction by taking advantage of the partial structure embedded in SMS texts and similarity comparisons are carried out using statistical methods. The proposed pipeline deals with major semantic variations across SMS data as well as makes it effective for its application on-device (mobile phone). To showcase the capabilities of our work, our pipeline has been designed with an inclination towards one of the possible applications of SMS text similarity discussed in one of the following sections but nonetheless guarantees scalability for other applications as well.

cs.CL↗

arXiv2020

On-Device Language Identification of Text in Images using Diacritic Characters

Diacritic characters can be considered as a unique set of characters providing us with adequate and significant clue in identifying a given language with considerably high accuracy. Diacritics, though associated with phonetics often serve as a distinguishing feature for many languages especially the ones with a Latin script. In this proposed work, we aim to identify language of text in images using the presence of diacritic characters in order to improve Optical Character Recognition (OCR) performance in any given automated environment. We showcase our work across 13 Latin languages encompassing 85 diacritic characters. We use an architecture similar to Squeezedet for object detection of diacritic characters followed by a shallow network to finally identify the language. OCR systems when accompanied with identified language parameter tends to produce better results than sole deployment of OCR systems. The discussed work apart from guaranteeing an improvement in OCR results also takes on-device (mobile phone) constraints into consideration in terms of model size and inference time.

cs.CV↗

arXiv2019

On The Role of Supermassive Black Holes in Quenching Star Formation in Local Central Galaxies

In this work, we analyze the role of AGN feedback in quenching star formation for massive, central galaxies in the local Universe. In particular, we compare the prediction of two semi-analytic models (L-GALAXIES and SAGE) featuring different schemes for AGN feedback, with the SDSS DR7 taking advantage of a novel technique for identifying central galaxies in an observational dataset. This enables us to study the correlation between the model passive fractions, which is predicted to be suppressed by feedback from an AGN, and the observed passive fractions in an observationally motivated parameter space. While the passive fractions for observed central galaxies show a good correlation with stellar mass and bulge mass, passive fractions in L-GALAXIES correlate with the halo and black hole mass. For SAGE, the passive fraction correlate with the bulge mass as well. Among the two models, SAGE has a smaller scatter in the black hole - bulge mass (M_BH - M_Bulge) relation and a slope that agrees better with the most recent observations at z \sim 0. Despite the more realistic prescription of radio mode feedback in SAGE, there are still tensions left with the observed passive fractions and the distribution of quenched galaxies. These tensions may be due to the treatment of galaxies living in non-resolved substructures and the resulting higher merger rates that could bring cold gas which is available for star formation.

astro-ph.GA↗