Jason Donald Eisner

US Patent:

20220327288, Oct 13, 2022

Filed:

Apr 13, 2021

Appl. No.:

17/229637

Inventors:

- Redmond WA, US
Adam D. PAULS - San Francisco CA, US
Daniel Louis KLEIN - Orinda CA, US
Eui Chul SHIN - San Francisco CA, US
Christopher H. LIN - Bellevue WA, US
Pengyu CHEN - Union City CA, US
Subhro ROY - Walnut Creek CA, US
Jason Michael EISNER - Baltimore MD, US
Benjamin Lev SNYDER - Bellevue WA, US
Samuel McIntire THOMSON - Berkeley CA, US

Assignee:

Microsoft Technology Licensing, LLC - Redmond WA

International Classification:

G06F 40/30
G06F 40/55
G06F 40/58
G06F 40/205

Abstract:

Systems and methods are provided for automatically generating a program based on a natural language utterance using semantic parsing. The semantic parsing includes translating a natural language utterance into instructions in a logical form for execution. The methods use a pre-trained natural language model and generate a canonical utterance as an intermediate form before generating the logical form. The natural language model may be an auto-regressive natural language model with a transformer to paraphrase a sequence of words or tokens in the natural language utterance. The methods generate a prompt including exemplar input/output pairs as a few-shot learning technique for the natural language model to predict words or tokens. The methods further use constrained decoding to determine a canonical utterance, iteratively selecting sequence of words as predicted by the model against rules for canonical utterances. The methods generate a program based on the canonical utterance for execution in an application.