no code implementations • 29 Nov 2023 • Tanmay Chavan, Shantanu Patankar, Aditya Kane, Omkar Gokhale, Geetanjali Kale, Raviraj Joshi
The results of the experiments strongly undermine the robustness of sentence encoders.
no code implementations • 4 Nov 2023 • Rajas Chitale, Ankit Vaidya, Aditya Kane, Archana Ghotkar
The majority of progress in continual learning has been stunted by the problem of catastrophic forgetting, which is caused by sequential training of the model on streams of data.
1 code implementation • 24 Jun 2023 • Tanmay Chavan, Omkar Gokhale, Aditya Kane, Shantanu Patankar, Raviraj Joshi
This is the first work that presents artifacts for code-mixed Marathi research.
1 code implementation • 6 Mar 2023 • Ankit Vaidya, Aditya Kane
Our proposed approach consists of a two-stage system and outperforms other participants' systems and previous works in this domain.
no code implementations • 20 Dec 2022 • Tanmay Chavan, Shantanu Patankar, Aditya Kane, Omkar Gokhale, Raviraj Joshi
The MahaTweetBERT, a BERT model, pre-trained on Marathi tweets when fine-tuned on the combined dataset (HASOC 2021 + HASOC 2022 + MahaHate), outperforms all models with an F1 score of 98. 43 on the HASOC 2022 test set.
no code implementations • 15 Oct 2022 • Tanmay Chavan, Aditya Kane
The spread of propaganda through the internet has increased drastically over the past years.
no code implementations • 15 Oct 2022 • Mihir Godbole, Parth Dandavate, Aditya Kane
This paper is an effort in this direction, where we explore methods for word sense disambiguation for the EvoNLP shared task.
1 code implementation • 9 Oct 2022 • Omkar Gokhale, Aditya Kane, Shantanu Patankar, Tanmay Chavan, Raviraj Joshi
Pre-training large neural language models, such as BERT, has led to impressive gains on many natural language processing (NLP) tasks.
1 code implementation • 21 Sep 2022 • Aditya Kane, V Manushree, Sahil Khose
Thus, we instead use pre-trained embeddings of text and image from this model for our supervised training and surpass previous state-of-the-art results on the FloodNet dataset.
no code implementations • 8 Sep 2022 • Neeraja Kirtane, V Manushree, Aditya Kane
Our major contributions in this paper are the construction of a novel corpus to evaluate occupational gender bias in Hindi, quantify this existing bias in these systems using a well-defined metric, and mitigate it by efficiently fine-tuning our model.
Bias Detection Cultural Vocal Bursts Intensity Prediction +1
1 code implementation • 30 May 2022 • Aditya Kane, Sahil Khose
Designing efficient and reliable VQA systems remains a challenging problem, more so in the case of disaster management and response systems.
no code implementations • WASSA (ACL) 2022 • Aditya Kane, Shantanu Patankar, Sahil Khose, Neeraja Kirtane
Detecting emotions in languages is important to accomplish a complete interaction between humans and machines.