no code implementations • SMM4H (COLING) 2022 • Alec Louis Candidato, Akshat Gupta, Xiaomo Liu, Sameena Shah
This paper presents our submission for the SMM4H 2022-Shared Task on the classification of self-reported intimate partner violence on Twitter (in English).
no code implementations • SMM4H (COLING) 2022 • Leung Wai Liu, Akshat Gupta, Saheed Obitayo, Xiaomo Liu, Sameena Shah
This paper presents my submission for Tasks 1 and 2 for the Social Media Mining of Health (SMM4H) 2022 Shared Tasks competition.
no code implementations • SMM4H (COLING) 2022 • Adrian Garcia Hernandez, Leung Wai Liu, Akshat Gupta, Vineeth Ravi, Saheed O. Obitayo, Xiaomo Liu, Sameena Shah
We present our response to Task 5 of the Social Media Mining for Health Applications (SMM4H) 2022 competition.
no code implementations • EACL (DravidianLangTech) 2021 • Akshat Gupta, Sai Krishna Rallabandi, Alan W Black
Sentiment analysis in Code-Mixed languages has garnered a lot of attention in recent years.
no code implementations • 1 May 2024 • Junsang Yoon, Akshat Gupta, Gopala Anumanchipalli
This study presents a targeted model editing analysis focused on the latest large language model, Llama-3.
no code implementations • 2 Apr 2024 • Saptarshi Dasgupta, Akshat Gupta, Shreshth Tuli, Rohan Paul
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.
2 code implementations • 21 Mar 2024 • Akshat Gupta, Dev Sajnani, Gopala Anumanchipalli
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.
1 code implementation • 11 Mar 2024 • Akshat Gupta, Sidharth Baskaran, Gopala Anumanchipalli
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.
no code implementations • 22 Feb 2024 • Xiaoyang Song, Yuta Adachi, Jessie Feng, Mouwei Lin, Linhao Yu, Frank Li, Akshat Gupta, Gopala Anumanchipalli, Simerjot Kaur
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.
no code implementations • 15 Jan 2024 • Akshat Gupta, Anurag Rao, Gopala Anumanchipalli
With this in mind, we evaluate the current model editing methods at scale, focusing on two state of the art methods: ROME and MEMIT.
no code implementations • 15 Sep 2023 • Akshat Gupta, Xiaoyang Song, Gopala Anumanchipalli
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.
no code implementations • 23 Aug 2023 • Akshat Gupta
Through a series of experiments, we first discover the characteristics of optimal prompts and model parameters for playing poker with these models.
1 code implementation • 17 Aug 2023 • Anant Singh, Akshat Gupta
Recent advancements in transformer-based speech representation models have greatly transformed speech processing.
no code implementations • 14 Jul 2023 • Akshat Gupta, Xiaomo Liu, Sameena Shah
A large body of literature tries to solve this problem by adapting models trained on the source domain to the target domain.
1 code implementation • 17 Jun 2023 • Akshat Gupta, Laxman Singh Tomar, Ridhima Garg
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
no code implementations • 12 Jun 2023 • Akshat Gupta
We also discuss the possible reasons for this and the relevance of quantifier understanding in evaluating language understanding in LLMs.
no code implementations • 24 May 2023 • Xiaoyang Song, Akshat Gupta, Kiyan Mohebbizadeh, Shujie Hu, Anant Singh
In this paper, we show that we do not yet have the right tools to measure personality in language models.
no code implementations • 22 May 2023 • Simerjot Kaur, Charese Smiley, Akshat Gupta, Joy Sain, Dongsheng Wang, Suchetha Siddagangappa, Toyin Aguda, Sameena Shah
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.
no code implementations • 31 Oct 2022 • Zihan Wang, Qi Meng, HaiFeng Lan, Xinrui Zhang, Kehao Guo, Akshat Gupta
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.
no code implementations • COLING (WNUT) 2022 • Alex Li, Ilyas Bankole-Hameed, Ranadeep Singh, Gabriel Shen Han Ng, Akshat Gupta
In hope of expanding training data, researchers often want to merge two or more datasets that are created using different labeling schemes.
no code implementations • 22 Sep 2022 • Alec Candidato, Akshat Gupta, Xiaomo Liu, Sameena Shah
This paper presents our submission for the SMM4H 2022-Shared Task on the classification of self-reported intimate partner violence on Twitter (in English).
no code implementations • NAACL (SIGMORPHON) 2022 • Akshat Gupta
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
no code implementations • 18 Oct 2021 • Hemant Yadav, Akshat Gupta, Sai Krishna Rallabandi, Alan W Black, Rajiv Ratn Shah
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
no code implementations • 1 Jul 2021 • Zhiyuan Guo, Yuexin Li, Guo Chen, Xingyu Chen, Akshat Gupta
Spoken dialogue systems such as Siri and Alexa provide great convenience to people's everyday life.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +6
no code implementations • 3 Apr 2021 • Akshat Gupta, Olivia Deng, Akruti Kushwaha, Saloni Mittal, William Zeng, Sai Krishna Rallabandi, Alan W Black
We build a word-free natural language understanding module that does intent recognition and slot identification from these phonetic transcription.
no code implementations • NAACL (CALCS) 2021 • Akshat Gupta, Sargam Menghani, Sai Krishna Rallabandi, Alan W Black
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.
no code implementations • 24 Feb 2021 • Akshat Gupta, Sai Krishna Rallabandi, Alan Black
Using task-specific pre-training and leveraging cross-lingual transfer are two of the most popular ways to handle code-switched data.
1 code implementation • EACL (DravidianLangTech) 2021 • Sai Muralidhar Jayanthi, Akshat Gupta
In this paper we present our submission for the EACL 2021-Shared Task on Offensive Language Identification in Dravidian languages.
no code implementations • 7 Nov 2020 • Akshat Gupta, Xinjian Li, Sai Krishna Rallabandi, Alan W Black
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
no code implementations • 9 Oct 2020 • Akshat Gupta, Sai Krishna Rallabandi, Alan W Black
Tremendous progress in speech and language processing has brought language technologies closer to daily human life.
1 code implementation • 25 Aug 2020 • Akshat Gupta, Milan Desai, Wusheng Liang, Magesh Kannan
Spatiotemporal action recognition is the task of locating and classifying actions in videos.
1 code implementation • 15 Jul 2020 • Manuel Ladron de Guevara, Christopher George, Akshat Gupta, Daragh Byrne, Ramesh Krishnamurti
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.
no code implementations • 20 Jun 2020 • Akshat Gupta, Prasad N R
In Blind Descent, gradients are not used to guide the learning process.
1 code implementation • 13 Dec 2019 • Gregory L. Eyink, Akshat Gupta, Tamer Zaki
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