Search Results for author:
Found 12 papers, 5 papers with code
SenTest: Evaluating Robustness of Sentence Encoders
The results of the experiments strongly undermine the robustness of sentence encoders.
Task Arithmetic with LoRA for Continual Learning
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.
My Boli: Code-mixed Marathi-English Corpora, Pretrained Language Models and Evaluation Benchmarks
This is the first work that presents artifacts for code-mixed Marathi research.
Two-stage Pipeline for Multilingual Dialect Detection
Our proposed approach consists of a two-stage system and outperforms other participants' systems and previous works in this domain.
A Twitter BERT Approach for Offensive Language Detection in Marathi
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.
Large Language Models for Multi-label Propaganda Detection
The spread of propaganda through the internet has increased drastically over the past years.
Temporal Word Meaning Disambiguation using TimeLMs
This paper is an effort in this direction, where we explore methods for word sense disambiguation for the EvoNLP shared task.
Spread Love Not Hate: Undermining the Importance of Hateful Pre-training for Hate Speech Detection
Pre-training large neural language models, such as BERT, has led to impressive gains on many natural language processing (NLP) tasks.
Continual VQA for Disaster Response Systems
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.
Efficient Gender Debiasing of Pre-trained Indic Language Models
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
An Efficient Modern Baseline for FloodNet VQA
Designing efficient and reliable VQA systems remains a challenging problem, more so in the case of disaster management and response systems.
Transformer based ensemble for emotion detection
Detecting emotions in languages is important to accomplish a complete interaction between humans and machines.
