Aditya Joshi
YOU?
Author Swipe
View article: A survey of classification tasks and approaches for legal contracts
A survey of classification tasks and approaches for legal contracts Open
Given the large size and volumes of contracts and their underlying inherent complexity, manual reviews become inefficient and prone to errors, creating a clear need for automation. Automatic Legal Contract Classification (LCC) revolutioniz…
View article: Towards Behavior Grammar-Driven IoT Network Traffic Generation using MUD Specifications
Towards Behavior Grammar-Driven IoT Network Traffic Generation using MUD Specifications Open
View article: Alternatives To Next Token Prediction In Text Generation -- A Survey
Alternatives To Next Token Prediction In Text Generation -- A Survey Open
The paradigm of Next Token Prediction (NTP) has driven the unprecedented success of Large Language Models (LLMs), but is also the source of their most persistent weaknesses such as poor long-term planning, error accumulation, and computati…
View article: Barriers to and strategies for improved treatment adherence in vitiligo: A systematic review
Barriers to and strategies for improved treatment adherence in vitiligo: A systematic review Open
View article: LLMs for Law: Evaluating Legal-Specific LLMs on Contract Understanding
LLMs for Law: Evaluating Legal-Specific LLMs on Contract Understanding Open
Despite advances in legal NLP, no comprehensive evaluation covering multiple legal-specific LLMs currently exists for contract classification tasks in contract understanding. To address this gap, we present an evaluation of 10 legal-specif…
View article: What am I missing here?: Evaluating Large Language Models for Masked Sentence Prediction
What am I missing here?: Evaluating Large Language Models for Masked Sentence Prediction Open
Transformer-based models primarily rely on Next Token Prediction (NTP), which predicts the next token in a sequence based on the preceding context. However, NTP's focus on single-token prediction often limits a model's ability to plan ahea…
View article: Electric Vehicle Charging Management: A Hybrid Optimization Review
Electric Vehicle Charging Management: A Hybrid Optimization Review Open
View article: Efficacy of an Automated Pulmonary Embolism (PE) Detection Algorithm on Routine Contrast-Enhanced Chest CT Imaging for Non-PE Studies
Efficacy of an Automated Pulmonary Embolism (PE) Detection Algorithm on Routine Contrast-Enhanced Chest CT Imaging for Non-PE Studies Open
The urgency to accelerate PE management and minimize patient risk has driven the development of artificial intelligence (AI) algorithms designed to provide a swift and accurate diagnosis in dedicated chest imaging (computed tomography pulm…
View article: Nek Minit: Harnessing Pragmatic Metacognitive Prompting for Explainable Sarcasm Detection of Australian and Indian English
Nek Minit: Harnessing Pragmatic Metacognitive Prompting for Explainable Sarcasm Detection of Australian and Indian English Open
Sarcasm is a challenge to sentiment analysis because of the incongruity between stated and implied sentiment. The challenge is exacerbated when the implication may be relevant to a specific country or geographical region. Pragmatic metacog…
View article: RACCOON: A Retrieval-Augmented Generation Approach for Location Coordinate Capture from News Articles
RACCOON: A Retrieval-Augmented Generation Approach for Location Coordinate Capture from News Articles Open
View article: A Survey on Multimodal Music Emotion Recognition
A Survey on Multimodal Music Emotion Recognition Open
Multimodal music emotion recognition (MMER) is an emerging discipline in music information retrieval that has experienced a surge in interest in recent years. This survey provides a comprehensive overview of the current state-of-the-art in…
View article: TRACE: Textual Relevance Augmentation and Contextual Encoding for Multimodal Hate Detection
TRACE: Textual Relevance Augmentation and Contextual Encoding for Multimodal Hate Detection Open
Social media memes are a challenging domain for hate detection because they intertwine visual and textual cues into culturally nuanced messages. To tackle these challenges, we introduce TRACE, a hierarchical multimodal framework that lever…
View article: RACCOON: A Retrieval-Augmented Generation Approach for Location Coordinate Capture from News Articles
RACCOON: A Retrieval-Augmented Generation Approach for Location Coordinate Capture from News Articles Open
Geocoding involves automatic extraction of location coordinates of incidents reported in news articles, and can be used for epidemic intelligence or disaster management. This paper introduces Retrieval-Augmented Coordinate Capture Of Onlin…
View article: Predicting the Target Word of Game-playing Conversations using a Low-Rank Dialect Adapter for Decoder Models
Predicting the Target Word of Game-playing Conversations using a Low-Rank Dialect Adapter for Decoder Models Open
View article: Risk – Return Computation of and Computation of the Optimal Portfolio of the Chosen Metal Sector Stocks from NSE
Risk – Return Computation of and Computation of the Optimal Portfolio of the Chosen Metal Sector Stocks from NSE Open
View article: BESSTIE: A Benchmark for Sentiment and Sarcasm Classification for Varieties of English
BESSTIE: A Benchmark for Sentiment and Sarcasm Classification for Varieties of English Open
View article: BESSTIE: A Benchmark for Sentiment and Sarcasm Classification for Varieties of English
BESSTIE: A Benchmark for Sentiment and Sarcasm Classification for Varieties of English Open
Despite large language models (LLMs) being known to exhibit bias against non-standard language varieties, there are no known labelled datasets for sentiment analysis of English. To address this gap, we introduce BESSTIE, a benchmark for se…
View article: Experiences from Creating a Benchmark for Sentiment Classification for Varieties of English
Experiences from Creating a Benchmark for Sentiment Classification for Varieties of English Open
Existing benchmarks often fail to account for linguistic diversity, like language variants of English. In this paper, we share our experiences from our ongoing project of building a sentiment classification benchmark for three variants of …
View article: "Is Hate Lost in Translation?": Evaluation of Multilingual LGBTQIA+ Hate Speech Detection
"Is Hate Lost in Translation?": Evaluation of Multilingual LGBTQIA+ Hate Speech Detection Open
This paper explores the challenges of detecting LGBTQIA+ hate speech of large language models across multiple languages, including English, Italian, Chinese and (code-switched) English-Tamil, examining the impact of machine translation and…
View article: Connecting Ideas in 'Lower-Resource' Scenarios: NLP for National Varieties, Creoles and Other Low-resource Scenarios
Connecting Ideas in 'Lower-Resource' Scenarios: NLP for National Varieties, Creoles and Other Low-resource Scenarios Open
Despite excellent results on benchmarks over a small subset of languages, large language models struggle to process text from languages situated in `lower-resource' scenarios such as dialects/sociolects (national or social varieties of a l…
View article: Predicting the Target Word of Game-playing Conversations using a Low-Rank Dialect Adapter for Decoder Models
Predicting the Target Word of Game-playing Conversations using a Low-Rank Dialect Adapter for Decoder Models Open
Dialect adapters that improve the performance of LLMs for NLU tasks on certain sociolects/dialects/national varieties ('dialects' for the sake of brevity) have been reported for encoder models. In this paper, we extend the idea of dialect …
View article: BAMBINO-LM: (Bilingual-)Human-Inspired Continual Pretraining of BabyLM
BAMBINO-LM: (Bilingual-)Human-Inspired Continual Pretraining of BabyLM Open
Children from bilingual backgrounds benefit from interactions with parents and teachers to re-acquire their heritage language. In this paper, we investigate how this insight from behavioral study can be incorporated into the learning of sm…
View article: Spectraformer: A Unified Random Feature Framework for Transformer
Spectraformer: A Unified Random Feature Framework for Transformer Open
Linearization of attention using various kernel approximation and kernel learning techniques has shown promise. Past methods used a subset of combinations of component functions and weight matrices within the random feature paradigm. We id…
View article: Striking a Balance between Classical and Deep Learning Approaches in Natural Language Processing Pedagogy
Striking a Balance between Classical and Deep Learning Approaches in Natural Language Processing Pedagogy Open
While deep learning approaches represent the state-of-the-art of natural language processing (NLP) today, classical algorithms and approaches still find a place in NLP textbooks and courses of recent years. This paper discusses the perspec…
View article: Evaluating Dialect Robustness of Language Models via Conversation Understanding
Evaluating Dialect Robustness of Language Models via Conversation Understanding Open
With an evergrowing number of LLMs reporting superlative performance for English, their ability to perform equitably for different dialects of English ($\textit{i.e.}$, dialect robustness) needs to be ascertained. Specifically, we use Engl…
View article: Natural Language Processing for Dialects of a Language: A Survey
Natural Language Processing for Dialects of a Language: A Survey Open
State-of-the-art natural language processing (NLP) models are trained on massive training corpora, and report a superlative performance on evaluation datasets. This survey delves into an important attribute of these datasets: the dialect o…
View article: Overview of the 2023 ICON Shared Task on Gendered Abuse Detection in Indic Languages
Overview of the 2023 ICON Shared Task on Gendered Abuse Detection in Indic Languages Open
This paper reports the findings of the ICON 2023 on Gendered Abuse Detection in Indic Languages. The shared task deals with the detection of gendered abuse in online text. The shared task was conducted as a part of ICON 2023, based on a no…
View article: Evaluation of Large Language Models Using an Indian Language LGBTI+ Lexicon
Evaluation of Large Language Models Using an Indian Language LGBTI+ Lexicon Open
Large language models (LLMs) are typically evaluated on the basis of task-based benchmarks such as MMLU. Such benchmarks do not examine the behaviour of LLMs in specific contexts. This is particularly true in the LGBTI+ context where socia…
View article: Relation Extraction from News Articles (RENA): A Tool for Epidemic Surveillance
Relation Extraction from News Articles (RENA): A Tool for Epidemic Surveillance Open
Relation Extraction from News Articles (RENA) is a browser-based tool designed to extract key entities and their semantic relationships in English language news articles related to infectious diseases. Constructed using the React framework…
View article: Stacking the Odds: Transformer-Based Ensemble for AI-Generated Text Detection
Stacking the Odds: Transformer-Based Ensemble for AI-Generated Text Detection Open
This paper reports our submission under the team name `SynthDetectives' to the ALTA 2023 Shared Task. We use a stacking ensemble of Transformers for the task of AI-generated text detection. Our approach is novel in terms of its choice of m…