公开(公告)号：US10963497B1

公开(公告)日：2021-03-30

申请号：US15083790

申请日：2016-03-29

Applicant: Amazon Technologies, Inc.

Inventor： Mihai Valentin Tablan ,  Sina Samangooei ,  Arpit Mittal ,  David Spike Palfrey ,  Emilio Monti ,  Pedro Ribeiro ,  Benjamin David Scott ,  Petra Elisabeth Holmes ,  Dianhuan Lin

IPC: G06F16/33

Abstract: A query parsing system uses a multi-stage process to parse the text of incoming queries before attempting to answer the queries. The multi-stage configuration involves a first trained classifier to determine the query type, or intent, of the text and a plurality of second trained classifiers, where each of the second trained classifiers is configured particularly for one specific respective query type. During query processing, the first trained classifier is used on the text to identify the query type. A second trained classifier for that specific identified query type is then found and used on the text to identify what strings in the text correspond to specific entities needed to resolve the query. The identified text strings and query type are then placed into a form understandable by a knowledge base and sent to the knowledge base for resolution. The classifiers may be trained using queries and answers previously processed by the knowledge base using a rules/template resolution process.

公开(公告)号：US09965726B1

公开(公告)日：2018-05-08

申请号：US14696214

申请日：2015-04-24

Applicant: Amazon Technologies, Inc.

Inventor： Mihai Valentin Tablan ,  Andrew Graham Fenn ,  David Spike Palfrey ,  Petra Elisabeth Holmes ,  Sina Samangooei

IPC: G06F15/18 ,  G06N3/00 ,  G06N3/12 ,  G06N99/00 ,  G06F17/30

CPC classification number: G06N99/005 ,  G06F17/30657 ,  G06F17/30867 ,  G06N3/126

Abstract: Techniques are described for adding knowledge to a knowledge base.

公开(公告)号：US11120341B1

公开(公告)日：2021-09-14

申请号：US14974634

申请日：2015-12-18

Applicant: Amazon Technologies, Inc.

Inventor： David Spike Palfrey ,  Sina Samangooei ,  Mihai Valentin Tablan ,  Maxime Peyrard

IPC: G06N5/02 ,  G06N5/04

Abstract: Techniques are described for determining the value of individual facts in a knowledge base, and various applications of such fact values. In one example, the knowledge base is part of a question answering system. A ranking of knowledge base facts based on the number of times each of the knowledge base facts is used in answering user questions (e.g., as determined from question answering logs) is used to derive a fact value function that may then be used to determine the value of other facts included in or subsequently added to the knowledge base.