no code implementations • 13 Feb 2024 • Aishwarya P S, Pranav Ajit Nair, Yashas Samaga, Toby Boyd, Sanjiv Kumar, Prateek Jain, Praneeth Netrapalli
On the PaLM2 pretraining dataset, a tandem of PaLM2-Bison and PaLM2-Gecko demonstrates a 3. 3% improvement in next-token prediction accuracy over a standalone PaLM2-Gecko, offering a 1. 16x speedup compared to a PaLM2-Otter model with comparable downstream performance.
1 code implementation • 26 May 2023 • Pranav Ajit Nair, Sukomal Pal, Pradeepika Verma
These source prefixes generate summaries for a small number of target domain documents.
1 code implementation • 24 May 2023 • Debayan Banerjee, Pranav Ajit Nair, Ricardo Usbeck, Chris Biemann
In this work, we analyse the role of output vocabulary for text-to-text (T2T) models on the task of SPARQL semantic parsing.
1 code implementation • 23 Mar 2023 • Debayan Banerjee, Pranav Ajit Nair, Ricardo Usbeck, Chris Biemann
To further improve the results, we instruct the model to produce a truncated version of the KG embedding for each entity.
1 code implementation • 27 Apr 2022 • Debayan Banerjee, Pranav Ajit Nair, Jivat Neet Kaur, Ricardo Usbeck, Chris Biemann
In this work, we focus on the task of generating SPARQL queries from natural language questions, which can then be executed on Knowledge Graphs (KGs).