Papers by Shirish Shevade

1 papers
Efficient Constituency Tree based Encoding for Natural Language to Bash Translation (2022.naacl-main)

Copied to clipboard

Challenge: Semantic parsing is one of the central tasks for natural language understanding (NLU).
Approach: They propose a Segmented Invocation Transformer that utilizes the information from the constituency parse tree of the natural language text and Bash command components to generate Bash commands.
Outcome: The proposed method improves the inference time and reduces the model parameters by 1.8x .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations