Search Results for author:
Found 7 papers, 4 papers with code
Multilingual Bias Detection and Mitigation for Indian Languages
Next, we investigate the effectiveness of popular multilingual Transformer-based models for the two tasks by modeling detection as a binary classification problem and mitigation as a style transfer problem.
Massively Multilingual Language Models for Cross Lingual Fact Extraction from Low Resource Indian Languages
Cross Lingual Information Extraction aims at extracting factual information in the form of English triples from low resource Indian Language text.
XF2T: Cross-lingual Fact-to-Text Generation for Low-Resource Languages
Our extensive experiments show that a multi-lingual mT5 model which uses fact-aware embeddings with structure-aware input encoding leads to best results on average across the twelve languages.
Ranked #1 on
Data-to-Text Generation
on XAlign
Adaptation of domain-specific transformer models with text oversampling for sentiment analysis of social media posts on Covid-19 vaccines
Covid-19 has spread across the world and several vaccines have been developed to counter its surge.
TLMOTE: A Topic-based Language Modelling Approach for Text Oversampling
To tackle the problem of bias towards majority classes, researchers have presented various techniques to oversample the minority class data points.
XAlign: Cross-lingual Fact-to-Text Alignment and Generation for Low-Resource Languages
Multiple critical scenarios (like Wikipedia text generation given English Infoboxes) need automated generation of descriptive text in low resource (LR) languages from English fact triples.
Ranked #3 on
Data-to-Text Generation
on XAlign
HI-MaNGA: Tracing the physics of the neutral and ionized ISM with the second data release
We present the second data release for the HI-MaNGA programme of HI follow-up observations for the SDSS-IV MaNGA survey.
Astrophysics of Galaxies
