Search Results for author: Gaurav Arora

Found 8 papers, 2 papers with code

Spartans@LT-EDI-EACL2021: Inclusive Speech Detection using Pretrained Language Models

no code implementations EACL (LTEDI) 2021 Megha Sharma, Gaurav Arora

We describe our system that ranked first in Hope Speech Detection (HSD) shared task and fourth in Offensive Language Identification (OLI) shared task, both in Tamil language.

Hope Speech Detection Language Identification +1

High-Resolution Satellite Imagery for Modeling the Impact of Aridification on Crop Production

no code implementations25 Sep 2022 Depanshu Sani, Sandeep Mahato, Parichya Sirohi, Saket Anand, Gaurav Arora, Charu Chandra Devshali, Thiagarajan Jayaraman, Harsh Kumar Agarwal

We also propose a yield prediction strategy that uses time-series data generated based on the observed growing season and the standard seasonal information obtained from Tamil Nadu Agricultural University for the region.

Time Series

Gauravarora@HASOC-Dravidian-CodeMix-FIRE2020: Pre-training ULMFiT on Synthetically Generated Code-Mixed Data for Hate Speech Detection

no code implementations5 Oct 2020 Gaurav Arora

We participated in both Sub-task A, which aims to identify offensive content in mixed-script (mixture of Native and Roman script) and Sub-task B, which aims to identify offensive content in Roman script, for Dravidian languages.

Hate Speech Detection

HINT3: Raising the bar for Intent Detection in the Wild

1 code implementation EMNLP (insights) 2020 Gaurav Arora, Chirag Jain, Manas Chaturvedi, Krupal Modi

Intent Detection systems in the real world are exposed to complexities of imbalanced datasets containing varying perception of intent, unintended correlations and domain-specific aberrations.

Intent Detection

iNLTK: Natural Language Toolkit for Indic Languages

1 code implementation EMNLP (NLPOSS) 2020 Gaurav Arora

We present iNLTK, an open-source NLP library consisting of pre-trained language models and out-of-the-box support for Data Augmentation, Textual Similarity, Sentence Embeddings, Word Embeddings, Tokenization and Text Generation in 13 Indic Languages.

Data Augmentation Paraphrase Generation +4

Does an LSTM forget more than a CNN? An empirical study of catastrophic forgetting in NLP

no code implementations ALTA 2019 Gaurav Arora, Afshin Rahimi, Timothy Baldwin

Catastrophic forgetting {---} whereby a model trained on one task is fine-tuned on a second, and in doing so, suffers a {``}catastrophic{''} drop in performance over the first task {---} is a hurdle in the development of better transfer learning techniques.

Continual Learning Transfer Learning

Attention based Sentence Extraction from Scientific Articles using Pseudo-Labeled data

no code implementations13 Feb 2018 Parth Mehta, Gaurav Arora, Prasenjit Majumder

We propose a new attention based deep learning architecture that jointly learns to identify important content, as well as the cue phrases that are indicative of summary worthy sentences.

Topic Models

Cannot find the paper you are looking for? You can Submit a new open access paper.