Papers by Saurabh Kumar
Regularized Graph Convolutional Networks for Short Text Classification (2020.coling-industry)
Copied to clipboard
| Challenge: | Short text classification is a problem in natural language processing, social network analysis, and e-commerce. |
| Approach: | They propose a short text classification technique that incorporates label dependencies into the output space to overcome the limitations of short text. |
| Outcome: | The proposed model outperforms baseline methods on proprietary and external datasets and is more robust to noise in textual features. |
IndiSentiment140: Sentiment Analysis Dataset for Indian Languages with Emphasis on Low-Resource Languages using Machine Translation (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing solutions to bridge the gap between resource-rich and resource-poor languages are being explored. |
| Approach: | They examine the feasibility of machine translation for creating sentiment analysis datasets in 22 Indian languages. |
| Outcome: | The proposed dataset can be used to tackle low-resource challenges in sentiment analysis for Indian languages. |
IndiSocialFT: Multilingual Word Representation for Indian languages in code-mixed environment (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies on word embeddings for Indian languages focus on monolingual corpora with limited reach to social media setups. |
| Approach: | They propose a generalized representation vector for diverse text characteristics . they use a FastText model to gather text from social media and well-formed sources . |
| Outcome: | The proposed representation vector surpasses baselines in most cases and languages, demonstrating suitability for various NLP applications. |
DUBLIN: Visual Document Understanding By Language-Image Network (2023.emnlp-industry)
Copied to clipboard
Kriti Aggarwal, Aditi Khandelwal, Kumar Tanmay, Owais Khan Mohammed, Qiang Liu, Monojit Choudhury, Hardik Chauhan, Subhojit Som, Vishrav Chaudhary, Saurabh Tiwary
| Challenge: | DUBLIN is a pixel-based visual document understanding model that does not rely on OCR. |
| Approach: | They propose a pixel-based visual document understanding model that does not rely on OCR. |
| Outcome: | The proposed model performs on extractive tasks such as DocVQA, InfoVQA and AI2D, and strong performance on abstraction datasets such as VisualMRC and text captioning. |