no code implementations • ICON 2021 • Swayatta Daw, Shivprasad Sagare, Tushar Abhishek, Vikram Pudi, Vasudeva Varma
We propose cross-lingual pairing of English triples with Hindi sentences to mitigate the unavailability of content overlap.
no code implementations • 23 Dec 2023 • Ankita Maity, Anubhav Sharma, Rudra Dhar, Tushar Abhishek, Manish Gupta, Vasudeva Varma
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.
no code implementations • 22 Sep 2022 • Shivprasad Sagare, Tushar Abhishek, Bhavyajeet Singh, Anubhav Sharma, Manish Gupta, Vasudeva Varma
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
1 code implementation • 1 Feb 2022 • Tushar Abhishek, Shivprasad Sagare, Bhavyajeet Singh, Anubhav Sharma, Manish Gupta, Vasudeva Varma
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
2 code implementations • 5 Sep 2021 • Tushar Abhishek, Daksh Rawat, Manish Gupta, Vasudeva Varma
Coherence is an important aspect of text quality and is crucial for ensuring its readability.
Ranked #1 on Coherence Evaluation on GCDC + RST - Accuracy