Semantic parsing of utterance using contractive paraphrasing

US12314670B2 · kind B2 · utility

Assignee

• MICROSOFT TECHNOLOGY LICENSING, LLC · US

Inventors

• Benjamin David VAN DURME · Baltimore, US
• Adam David Pauls · San Francisco, US
• Daniel Klein · Orinda, US
• Eui Chul SHIN · San Francisco, US
• Christopher H. LIN · Bellevue, US
• Pengyu Chen · Cupertino, US
• Subhro ROY · Walnut Creek, US
• Emmanouil Antonios Platanios · Pittsburgh, US
• Jason M. Eisner · Baltimore, US
• Benjamin Lev Snyder · Worcester, US
• Samuel McIntire THOMSON · Berkeley, US

Key dates

• Filing date: Apr 13, 2021
• Grant date: May 27, 2025
• Expiry date: Dec 9, 2041

Classification

• Technology area (CPC G): Physics
• CPC primary: G06N20/00
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

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.