Aditi Chaudhary
YOU?
Author Swipe
View article: Refract ICL: Rethinking Example Selection in the Era of Million-Token Models
Refract ICL: Rethinking Example Selection in the Era of Million-Token Models Open
The emergence of long-context large language models (LLMs) has enabled the use of hundreds, or even thousands, of demonstrations for in-context learning (ICL) - a previously impractical regime. This paper investigates whether traditional I…
View article: Time To End Caste Based Discrimination In Prisons In India: A Significant Law Reform In Response To The Directions Of The Supreme Court
Time To End Caste Based Discrimination In Prisons In India: A Significant Law Reform In Response To The Directions Of The Supreme Court Open
In the wake of recent order of the Supreme Court on the issue of caste-based discrimination of prisoners, 'Model Prison Manual, 2016' and the 'Model Prisons and Correctional Services Act, 2023' have been amended. As per the new addition in…
View article: <p>Time To End Caste Based Discrimination in Prisons in India: A Significant Law Reform in Response to the Directions of the Supreme Court</p>
Time To End Caste Based Discrimination in Prisons in India: A Significant Law Reform in Response to the Directions of the Supreme Court Open
View article: Herbal Remedies Effective on Treating Idiopathic Pulmonary Fibrosis
Herbal Remedies Effective on Treating Idiopathic Pulmonary Fibrosis Open
Idiopathic Pulmonary Fibrosis (IPF) poses a significant challenge in the realm of respiratory diseases, characterized by progressive lung scarring and compromised breathing function. While conventional medical interventions provide some re…
View article: Eco-Fashion Trends: Examining The Determinants of Green Apparel Purchasing Decisions
Eco-Fashion Trends: Examining The Determinants of Green Apparel Purchasing Decisions Open
View article: Exploring The Link Between Environmental Concern and Green Apparel Buying Behavior: A Review
Exploring The Link Between Environmental Concern and Green Apparel Buying Behavior: A Review Open
View article: It's All Relative! -- A Synthetic Query Generation Approach for Improving Zero-Shot Relevance Prediction
It's All Relative! -- A Synthetic Query Generation Approach for Improving Zero-Shot Relevance Prediction Open
Recent developments in large language models (LLMs) have shown promise in their ability to generate synthetic query-document pairs by prompting with as few as 8 demonstrations. This has enabled building better IR models, especially for tas…
View article: Teacher Perception of Automatically Extracted Grammar Concepts for L2 Language Learning
Teacher Perception of Automatically Extracted Grammar Concepts for L2 Language Learning Open
One of the challenges in language teaching is how best to organize rules regarding syntax, semantics, or phonology in a meaningful manner. This not only requires content creators to have pedagogical skills, but also have that language's de…
View article: Crossing the Threshold: Idiomatic Machine Translation through Retrieval Augmentation and Loss Weighting
Crossing the Threshold: Idiomatic Machine Translation through Retrieval Augmentation and Loss Weighting Open
Idioms are common in everyday language, but often pose a challenge to translators because their meanings do not follow from the meanings of their parts. Despite significant advances, machine translation systems still struggle to translate …
View article: Data Leakage in Cloud System
Data Leakage in Cloud System Open
The issue of data leakage is more prevalent in a cloud computing en- vironment. The data distributor transfers such sensitive data to the agents and some of the data gets leaked, the technique of finding a guilty agent talked about here is…
View article: Ambiguity-Aware In-Context Learning with Large Language Models
Ambiguity-Aware In-Context Learning with Large Language Models Open
In-context learning (ICL) i.e. showing LLMs only a few task-specific demonstrations has led to downstream gains with no task-specific fine-tuning required. However, LLMs are sensitive to the choice of prompts, and therefore a crucial resea…
View article: A Novel Approach for Customer Churn Prediction in Telecom using Machine Learning Models
A Novel Approach for Customer Churn Prediction in Telecom using Machine Learning Models Open
For organizations across a range of industries, customer churn is a serious problem.Businesses must identify consumers who are in danger of leaving in order totake actions to keep them. By examining previous data and seeing trends indicati…
View article: A Systemic Summary of Nanotechnology's Current and Prospective Scope in Drugs Delivery
A Systemic Summary of Nanotechnology's Current and Prospective Scope in Drugs Delivery Open
The creation of drug formulations based on nanoparticles offers the possibility to tackle and treat challenging diseases. The size of nanoparticles varies between 100 and 500 nm. By changing their size, surface characteristics, and structu…
View article: A Systemic Summary of Nanotechnology's Current and Prospective Scope in Drugs Delivery
A Systemic Summary of Nanotechnology's Current and Prospective Scope in Drugs Delivery Open
The creation of drug formulations based on nanoparticles offers the possibility to tackle and treat challenging diseases. The size of nanoparticles varies between 100 and 500 nm. By changing their size, surface characteristics, and structu…
View article: Exploring the Viability of Synthetic Query Generation for Relevance Prediction
Exploring the Viability of Synthetic Query Generation for Relevance Prediction Open
Query-document relevance prediction is a critical problem in Information Retrieval systems. This problem has increasingly been tackled using (pretrained) transformer-based models which are finetuned using large collections of labeled data.…
View article: Salient Span Masking for Temporal Understanding
Salient Span Masking for Temporal Understanding Open
Salient Span Masking (SSM) has shown itself to be an effective strategy to improve closed-book question answering performance. SSM extends general masked language model pretraining by creating additional unsupervised training sentences tha…
View article: Teacher Perception of Automatically Extracted Grammar Concepts for L2 Language Learning
Teacher Perception of Automatically Extracted Grammar Concepts for L2 Language Learning Open
One of the challenges in language teaching is how best to organize rules regarding syntax, semantics, or phonology in a meaningful manner. This not only requires content creators to have pedagogical skills, but also have that language’s de…
View article: Crossing the Threshold: Idiomatic Machine Translation through Retrieval Augmentation and Loss Weighting
Crossing the Threshold: Idiomatic Machine Translation through Retrieval Augmentation and Loss Weighting Open
Idioms are common in everyday language, but often pose a challenge to translators because their meanings do not follow from the meanings of their parts. Despite significant advances, machine translation systems still struggle to translate …
View article: Salient Span Masking for Temporal Understanding
Salient Span Masking for Temporal Understanding Open
Salient Span Masking (SSM) has shown itself to be an effective strategy to improve closed-book question answering performance. SSM extends general masked language model pretraining by creating additional unsupervised training sentences tha…
View article: Preparation and Evaluation of Niosomes for the Delivery of Antioxidant to the Skin for Antiaging Purpose
Preparation and Evaluation of Niosomes for the Delivery of Antioxidant to the Skin for Antiaging Purpose Open
Niosomes are unilamellar or multilamellar vesicles capable of entrapping hydrophilic and hydrophobic solutes. Niosomes are promising drug carriers as they possess greater stability. Niosomes is currently reported to increase drug stability…
View article: Teacher Perception of Automatically Extracted Grammar Concepts for L2 Language Learning
Teacher Perception of Automatically Extracted Grammar Concepts for L2 Language Learning Open
One of the challenges of language teaching is how to organize the rules regarding syntax, semantics, or phonology of the language in a meaningful manner. This not only requires pedagogical skills, but also requires a deep understanding of …
View article: AUTOLEX: An Automatic Framework for Linguistic Exploration
AUTOLEX: An Automatic Framework for Linguistic Exploration Open
Each language has its own complex systems of word, phrase, and sentence construction, the guiding principles of which are often summarized in grammar descriptions for the consumption of linguists or language learners. However, manual creat…
View article: Proceedings of the Fifth Workshop on the Use of Computational Methods in the Study of Endangered Languages
Proceedings of the Fifth Workshop on the Use of Computational Methods in the Study of Endangered Languages Open
In this paper we present the speech corpus for the Siberian Ingrian Finnish language.The speech corpus includes: audio data, annotations, software tools for data processing, two databases and a web application.We have published part of the…
View article: Menstrual hygiene: an important prognosticator of excessive vaginal bleeding in the high focused states of India
Menstrual hygiene: an important prognosticator of excessive vaginal bleeding in the high focused states of India Open
Background: There is increasing evidence of challenges that girls and women face in managing menstruation and vaginal bleeding. In many societies, these are handled behind the scenes as cultural taboos. Objectives: The study aims to addres…
View article: When is Wall a Pared and when a Muro? -- Extracting Rules Governing Lexical Selection
When is Wall a Pared and when a Muro? -- Extracting Rules Governing Lexical Selection Open
Learning fine-grained distinctions between vocabulary items is a key challenge in learning a new language. For example, the noun "wall" has different lexical manifestations in Spanish -- "pared" refers to an indoor wall while "muro" refers…
View article: Tweet Retrieval and Analysing the Trends
Tweet Retrieval and Analysing the Trends Open
We can’t disregard the importance of Social Media in Today’s Technology Era. Internet is almost in every hand. People uses various Social Media platforms to express themselves and their thinking about various topics such as Politics, Enter…
View article: Do Context-Aware Translation Models Pay the Right Attention?
Do Context-Aware Translation Models Pay the Right Attention? Open
Context-aware machine translation models are designed to leverage contextual information, but often fail to do so. As a result, they inaccurately disambiguate pronouns and polysemous words that require context for resolution. In this paper…
View article: Evaluating the Morphosyntactic Well-formedness of Generated Texts
Evaluating the Morphosyntactic Well-formedness of Generated Texts Open
Text generation systems are ubiquitous in natural language processing applications. However, evaluation of these systems remains a challenge, especially in multilingual settings. In this paper, we propose L'AMBRE -- a metric to evaluate th…
View article: Reducing Confusion in Active Learning for Part-Of-Speech Tagging
Reducing Confusion in Active Learning for Part-Of-Speech Tagging Open
Active learning (AL) uses a data selection algorithm to select useful training samples to minimize annotation cost. This is now an essential tool for building low-resource syntactic analyzers such as part-of-speech (POS) taggers. Existing …
View article: Emperical study on female harassment at different workplaces in India
Emperical study on female harassment at different workplaces in India Open
Sexual harassment has really become a matter of worry in today's world. The current report shows an in-depth analysis of sexual harassment of female at different workplaces. In India, in the seminal judgment of the Supreme Court in Vishaka…