US 12,265,528 B1
Natural language query processing
Wuwei Lan, La Jolla, CA (US); Patrick Ng, Great Neck, NY (US); Zhiguo Wang, Syosset, NY (US); Ramesh M. Nallapati, San Jose, CA (US); Henghui Zhu, Jersey City, NJ (US); Anuj Chauhan, New York, NY (US); Sudipta Sengupta, Bellevue, WA (US); Stephen Michael Ash, Seattle, WA (US); Bing Xiang, Mount Kisco, NY (US); and Gregory David Adams, Seattle, WA (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on Mar. 21, 2023, as Appl. No. 18/187,553.
Int. Cl. G06F 16/00 (2019.01); G06F 16/22 (2019.01); G06F 16/242 (2019.01); G06F 16/2457 (2019.01); G06F 16/248 (2019.01); G06F 16/25 (2019.01); G06N 3/0455 (2023.01); G06N 3/0499 (2023.01)
CPC G06F 16/243 (2019.01) [G06F 16/221 (2019.01); G06F 16/24578 (2019.01); G06F 16/248 (2019.01); G06F 16/258 (2019.01); G06N 3/0455 (2023.01); G06N 3/0499 (2023.01)] 18 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
receiving a natural language query (NLQ);
performing a lexical query to retrieve a set of candidate datasets for the NLQ;
performing named entity recognition (NER) on the NLQ to identify a set of named entities;
performing named entity linking (NEL) to link the set of named entities to corresponding columns or cells in the set of candidate datasets;
based on performing the NEL, selecting a set of top-K candidate datasets from the set of candidate datasets;
generating an intent representation (IR) using a sequence-to-sequence (S2S) machine learning model, the NLQ, and the set of top-K candidate datasets; and
generating a visualization for the intent representation (IR).