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.
1 code implementation • 22 Mar 2023 • Dhaval Taunk, Shivprasad Sagare, Anupam Patil, Shivansh Subramanian, Manish Gupta, Vasudeva Varma
But, for low-resource languages, the scarcity of reference articles makes monolingual summarization ineffective in solving this problem.
Ranked #1 on Cross-Lingual Abstractive Summarization on XWikiRef
Cross-Lingual Abstractive Summarization Document Summarization +3
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