Search Results for author:
Found 33 papers, 8 papers with code
Task-Specific Pre-Training and Cross Lingual Transfer for Sentiment Analysis in Dravidian Code-Switched Languages
Sentiment analysis in Code-Mixed languages has garnered a lot of attention in recent years.
AIR-JPMC@SMM4H’22: BERT + Ensembling = Too Cool: Using Multiple BERT Models Together for Various COVID-19 Tweet Identification Tasks
This paper presents my submission for Tasks 1 and 2 for the Social Media Mining of Health (SMM4H) 2022 Shared Tasks competition.
AIR-JPMC@SMM4H’22: Identifying Self-Reported Spanish COVID-19 Symptom Tweets Through Multiple-Model Ensembling
We present our response to Task 5 of the Social Media Mining for Health Applications (SMM4H) 2022 competition.
AIR-JPMC@SMM4H’22: Classifying Self-Reported Intimate Partner Violence in Tweets with Multiple BERT-based Models
This paper presents our submission for the SMM4H 2022-Shared Task on the classification of self-reported intimate partner violence on Twitter (in English).
Uncertainty-aware Active Learning of NeRF-based Object Models for Robot Manipulators using Visual and Re-orientation Actions
This paper presents an approach that enables a robot to rapidly learn the complete 3D model of a given object for manipulation in unfamiliar orientations.
A Unified Framework for Model Editing
We introduce a unifying framework that brings two leading "locate-and-edit" model editing techniques -- ROME and MEMIT -- under a single conceptual umbrella, optimizing for the same goal, which we call the preservation-memorization objective.
Rebuilding ROME : Resolving Model Collapse during Sequential Model Editing
With this paper, we provide a more stable implementation ROME, which we call r-ROME and show that model collapse is no longer observed when making large scale sequential edits with r-ROME, while further improving generalization and locality of model editing compared to the original implementation of ROME.
Identifying Multiple Personalities in Large Language Models with External Evaluation
In this paper, we investigate LLM personalities using an alternate personality measurement method, which we refer to as the external evaluation method, where instead of prompting LLMs with multiple-choice questions in the Likert scale, we evaluate LLMs' personalities by analyzing their responses toward open-ended situational questions using an external machine learning model.
Model Editing at Scale leads to Gradual and Catastrophic Forgetting
With this in mind, we evaluate the current model editing methods at scale, focusing on two state of the art methods: ROME and MEMIT.
Self-Assessment Tests are Unreliable Measures of LLM Personality
These simple tests, done on ChatGPT and three Llama2 models of different sizes, show that self-assessment personality tests created for humans are unreliable measures of personality in LLMs.
Are ChatGPT and GPT-4 Good Poker Players? -- A Pre-Flop Analysis
Through a series of experiments, we first discover the characteristics of optimal prompts and model parameters for playing poker with these models.
Decoding Emotions: A comprehensive Multilingual Study of Speech Models for Speech Emotion Recognition
Recent advancements in transformer-based speech representation models have greatly transformed speech processing.
Unsupervised Domain Adaptation using Lexical Transformations and Label Injection for Twitter Data
A large body of literature tries to solve this problem by adapting models trained on the source domain to the target domain.
GlyphNet: Homoglyph domains dataset and detection using attention-based Convolutional Neural Networks
Nevertheless, the problem with both methods is that they require paired sequences of real and fake domain strings to work with, which is often not the case in the real world, as the attacker only sends the illegitimate or homoglyph domain to the vulnerable user.
Ranked #1 on
Binary Classification
on Glyphnet Dataset
Probing Quantifier Comprehension in Large Language Models: Another Example of Inverse Scaling
We also discuss the possible reasons for this and the relevance of quantifier understanding in evaluating language understanding in LLMs.
Have Large Language Models Developed a Personality?: Applicability of Self-Assessment Tests in Measuring Personality in LLMs
In this paper, we show that we do not yet have the right tools to measure personality in language models.
REFinD: Relation Extraction Financial Dataset
A number of datasets for Relation Extraction (RE) have been created to aide downstream tasks such as information retrieval, semantic search, question answering and textual entailment.
Multilingual Speech Emotion Recognition With Multi-Gating Mechanism and Neural Architecture Search
While Speech Emotion Recognition (SER) is a common application for popular languages, it continues to be a problem for low-resourced languages, i. e., languages with no pretrained speech-to-text recognition models.
TransPOS: Transformers for Consolidating Different POS Tagset Datasets
In hope of expanding training data, researchers often want to merge two or more datasets that are created using different labeling schemes.
AIR-JPMC@SMM4H'22: Classifying Self-Reported Intimate Partner Violence in Tweets with Multiple BERT-based Models
This paper presents our submission for the SMM4H 2022-Shared Task on the classification of self-reported intimate partner violence on Twitter (in English).
On Building Spoken Language Understanding Systems for Low Resourced Languages
We test our system on Belgian Dutch (Flemish) and English and find that using phonetic transcriptions to make intent classification systems in such low-resourced setting performs significantly better than using speech features.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Intent Classification Using Pre-trained Language Agnostic Embeddings For Low Resource Languages
We perform experiments across three different languages: English, Sinhala, and Tamil each with different data sizes to simulate high, medium, and low resource scenarios.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Word-Free Spoken Language Understanding for Mandarin-Chinese
Spoken dialogue systems such as Siri and Alexa provide great convenience to people's everyday life.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+6
Intent Recognition and Unsupervised Slot Identification for Low Resourced Spoken Dialog Systems
We build a word-free natural language understanding module that does intent recognition and slot identification from these phonetic transcription.
Unsupervised Self-Training for Sentiment Analysis of Code-Switched Data
We propose a general framework called Unsupervised Self-Training and show its applications for the specific use case of sentiment analysis of code-switched data.
Task-Specific Pre-Training and Cross Lingual Transfer for Code-Switched Data
Using task-specific pre-training and leveraging cross-lingual transfer are two of the most popular ways to handle code-switched data.
SJ_AJ@DravidianLangTech-EACL2021: Task-Adaptive Pre-Training of Multilingual BERT models for Offensive Language Identification
In this paper we present our submission for the EACL 2021-Shared Task on Offensive Language Identification in Dravidian languages.
Acoustics Based Intent Recognition Using Discovered Phonetic Units for Low Resource Languages
With the aim of aiding development of spoken dialog systems in low resourced languages, we propose a novel acoustics based intent recognition system that uses discovered phonetic units for intent classification.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
Mere account mein kitna balance hai? -- On building voice enabled Banking Services for Multilingual Communities
Tremendous progress in speech and language processing has brought language technologies closer to daily human life.
Spatiotemporal Action Recognition in Restaurant Videos
Spatiotemporal action recognition is the task of locating and classifying actions in videos.
Multimodal Word Sense Disambiguation in Creative Practice
We present a dataset, Ambiguous Descriptions of Art Images (ADARI), of contemporary workpieces, which aims to provide a foundational resource for subjective image description and multimodal word disambiguation in the context of creative practice.
Blind Descent: A Prequel to Gradient Descent
In Blind Descent, gradients are not used to guide the learning process.
Stochastic Lagrangian Dynamics of Vorticity. I. General Theory
Prior mathematical work of Constantin and Iyer (2008, 2011) has shown that incompressible Navier-Stokes solutions possess infinitely-many stochastic Lagrangian conservation laws for vorticity, backward in time, which generalize the invariants of Cauchy (1815) for smooth Euler solutions.
Fluid Dynamics Superconductivity Mathematical Physics Mathematical Physics Computational Physics
