Method, electronic device and storage medium for semantic parsing

Patent metadata

Field	Value
Publication number	US-2022350972-A1
Application number	US-202117519515-A
Country	US
Kind code	A1
Filing date	Nov 4, 2021
Priority date	Apr 29, 2021
Publication date	Nov 3, 2022
Grant date	—

Abstract

Methods, electronic device, and non-transitory computer-readable storage mediums are provided for semantic parsing. The equipment may obtain a first recognition result of a target statement. The first recognition result may include a first intention recognition result and a first entity recognition result. The first entity recognition result may correspond to a plurality of vertical domains. The equipment may also determine one of the plurality of vertical domains corresponding to the first entity recognition result as a target vertical domain corresponding to the target statement according to the first intention recognition result. The equipment may further convert the first entity recognition result into a second entity recognition result in the target vertical domain. The equipment may also parse an intention of the target statement according to the second entity recognition result.

First claim

What is claimed is:

1 . A method for semantic parsing, comprising:
obtaining a first recognition result of a target statement, wherein the first recognition result comprises a first intention recognition result and a first entity recognition result, and wherein the first entity recognition result corresponds to a plurality of vertical domains; determining one of the plurality of vertical domains corresponding to the first entity recognition result as a target vertical domain corresponding to the target statement according to the first intention recognition result; converting the first entity recognition result into a second entity recognition result in the target vertical domain; and parsing an intention of the target statement according to the second entity recognition result.

2 . The method according to claim 1 , further comprising:
establishing, before obtaining the first recognition result of the target statement, at least one first slot and a first intention corresponding to the at least one first slot; performing mapping of the target vertical domain to the first slots and establishing an association relationship between second slots and the first slots in the target vertical domain, wherein each of the second slots corresponds to one first slot, wherein each of the first slots corresponds to at least one second slot, and wherein a total quantity of the first slots is smaller than or equal to that of the second slots, and associating the target vertical domain to the first intention.

3 . The method according to claim 2 , further comprising:
generating training samples according to the first slots and the first intention, wherein the training samples comprise positive samples and negative samples of the target vertical domain; and training a first recognition model by using the training samples.

4 . The method according to claim 3 , wherein obtaining the first recognition result of the target statement comprises:
inputting the target statement into the first recognition model so as to obtain the first recognition result.

5 . The method according to claim 4 , further comprising:
collecting a recognition result of the first recognition model; and adding the recognition result into the training samples.

6 . The method according to claim 2 , wherein the first entity recognition result comprises an entity recognition result of at least one first slot, and wherein converting the first entity recognition result into the second entity recognition result in the target vertical domain comprises:
obtaining a corresponding relation between all the second slots and the first slots in the target vertical domain; and determining an entity recognition result of the corresponding second slots according to the entity recognition result of the first slots so as to generate the second entity recognition result in the target vertical domain.

7 . The method according to claim 1 , wherein parsing the intention of the target statement according to the second entity recognition result comprises:
parsing the intention of the target statement according to the second entity recognition result and keywords of the target statement.

8 . The method according to claim 1 , further comprising:
generating and outputting, after parsing the intention of the target statement according to the second entity recognition result, a query statement for the target statement according to the second entity recognition result in the target vertical domain and the intention of the target statement.

9 . An electronic device, comprising:
one or more processors; and a non-transitory computer readable storage medium, configured to store instructions executable by the one or more processors; wherein the one or more processors are configured to:
obtain a first recognition result of a target statement, wherein the first recognition result comprises a first intention recognition result and a first entity recognition result, and wherein the first entity recognition result corresponds to a plurality of vertical domains;
determine one of the plurality of vertical domains corresponding to the first entity recognition result as a target vertical domain corresponding to the target statement according to the first intention recognition result;
convert the first entity recognition result into a second entity recognition result in the target vertical domain; and
parse an intention of the target statement according to the second entity recognition result.

10 . The electronic device according to claim 9 , wherein the one or more processors are further configured to:
establish at least one first slot and a first intention corresponding to the at least one first slot; perform mapping of the target vertical domain to the first slots and establish an association relationship between second slots and the first slots in the target vertical domain, wherein each of the second slots corresponds to one first slot, each of the first slots corresponds to at least one second slot, and a total quantity of the first slots is smaller than or equal to that of the second slots; and associate the target vertical domain to the first intention.

11 . The electronic device according to claim 10 , wherein the one or more processors are further configured to:
generate training samples according to the first slots and the first intention, wherein the training samples comprise positive samples and negative samples of the target vertical domain; and train a first recognition model by using the training samples.

12 . The electronic device according to claim 11 , wherein the one or more processors configured to obtain the first recognition result of the target statement are further configured to:
input the target statement into the first recognition model so as to obtain the first recognition result.

13 . The electronic device according to claim 12 , wherein the one or more processors are further configured to:
collect a recognition result of the first recognition model; and add the recognition result into the training samples.

14 . The electronic device according to claim 10 , wherein the first entity recognition result comprises an entity recognition result of at least one first slot, and wherein the one or more processors configured to convert the first entity recognition result into the second entity recognition are further configured to:
obtain a corresponding relation between all the second slots and the first slots in the target vertical domain; and determine an entity recognition result of the corresponding second slots according to the entity recognition result of the first slots so as to generate the second entity recognition result in the target vertical domain.

15 . The electronic device according to claim 9 , wherein the one or more processors configured to parse the intention of the target statement according to the second entity recognition are further configured to:
parse the intention of the target statement according to the second entity recognition result and keywords of the target statement.

16 . The electronic device according to claim 9 , wherein the one or more processors are further configured to:
generate and output a query statement for the target statement according to the second entity recognition result in the target vertical domain and the intention of the target statement after parsing the intention of the target statement according to the second entity recognition result.

17 . A non-transitory computer readable storage medium, having stored therein in

Assignees

• Beijing Xiaomi Mobile Software Co Ltd
• Beijing Xiaomi Pinecone Electronics Co Ltd

Inventors

• Xu Dezhi
• Dai Wen
• Liu Yan
• Liu Huiwen
• Chen Shuai

Classifications

• G06N3/044

  Recurrent networks, e.g. Hopfield networks · CPC title

• G06F40/30 Primary

  Semantic analysis · CPC title

• G06F40/205

  Parsing · CPC title

• G06F40/295 Primary

  Named entity recognition · CPC title

• G06N3/08

  Learning methods · CPC title