8 citations · 12 across the 3 of their papers we have counts for
3 papers
cs.CL2022★ 3 cited
MMTM: Multi-Tasking Multi-Decoder Transformer for Math Word Problems
Keyur Faldu, Amit Sheth, Prashant Kikani +1
Recently, quite a few novel neural architectures were derived to solve math word problems by predicting expression trees. These architectures varied from seq2seq models, including…
cs.CL2021★ 1 cited
Towards Tractable Mathematical Reasoning: Challenges, Strategies, and Opportunities for Solving Math Word Problems
Keyur Faldu, Amit Sheth, Prashant Kikani +2
Mathematical reasoning would be one of the next frontiers for artificial intelligence to make significant progress. The ongoing surge to solve math word problems (MWPs) and hence a…
cs.CL2021★ 8 cited
KI-BERT: Infusing Knowledge Context for Better Language and Domain Understanding
Keyur Faldu, Amit Sheth, Prashant Kikani +1
Contextualized entity representations learned by state-of-the-art transformer-based language models (TLMs) like BERT, GPT, T5, etc., leverage the attention mechanism to learn the d…