MMTM: Multi-Tasking Multi-Decoder Transformer for Math Word Problems

no code implementations • 2 Jun 2022 • Keyur Faldu, Amit Sheth, Prashant Kikani, Darshan Patel

Recently, quite a few novel neural architectures were derived to solve math word problems by predicting expression trees.

Decoder Math +1

Towards Tractable Mathematical Reasoning: Challenges, Strategies, and Opportunities for Solving Math Word Problems

no code implementations • 29 Oct 2021 • Keyur Faldu, Amit Sheth, Prashant Kikani, Manas Gaur, Aditi Avasthi

Mathematical reasoning would be one of the next frontiers for artificial intelligence to make significant progress.

Answer Generation Math +2

KI-BERT: Infusing Knowledge Context for Better Language and Domain Understanding

no code implementations • 9 Apr 2021 • Keyur Faldu, Amit Sheth, Prashant Kikani, Hemang Akbari

We take BERT as a baseline model and implement the "Knowledge-Infused BERT" by infusing knowledge context from ConceptNet and WordNet, which significantly outperforms BERT and other recent knowledge-aware BERT variants like ERNIE, SenseBERT, and BERT_CS over eight different subtasks of GLUE benchmark.

Knowledge Graph Embedding Knowledge Graph Embeddings +3