Systems and methods for handling multilingual queries
Systems and methods for handling multilingual queries are provided. One example method includes receiving, at a computing device, an input, wherein the input comprises a multi-lingual query comprising at least a first source language and a second source language. The multi-lingual query is translated, word for word, into a destination language to produce a monolingual query, with the word order of the multilingual query and the word order of the monolingual query being the same. The monolingual query is processed using natural language processing to map the mono-lingual query to a natural language query in the destination language.
1. A method comprising:
receiving, at a computing device, a multilingual query comprising at least a first source language and a second source language;
selecting, based on a language associated with the computing device, a destination language;
for words of the multilingual query that are in a source language other than the destination language, translating, word for word, the words into the destination language to produce a monolingual query, wherein a word order of the multilingual query and a word order of the monolingual query are the same;
identifying a trained network that has been trained on the first source language and the second source language;
inputting the monolingual query into the trained network to map the monolingual query to a natural language query in the destination language; and
generating for output, at the computing device and based on the natural language query, a response to the multilingual query.
2. The method of claim 1 , wherein at least one of the translating or the mapping the monolingual query to the natural language query in the destination language is performed at the computing device.
3. The method of claim 1 , wherein:
the computing device communicates with a server, and
the server performs at least one of the translating or the mapping the monolingual query to the natural language query in the destination language.
4. The method of claim 1 , wherein the mapping the monolingual query to the natural language query in the destination language further comprises utilizing the trained network, wherein the trained network comprises a hidden state based on a word order of the destination language.
5. The method of claim 1 , wherein receiving the multilingual query further comprises receiving the multilingual query comprising a spoken input or a text input.
6. The method of claim 1 , wherein the selecting the destination language further comprises selecting the destination language with one of a machine learning model or a neural network model.
7. The method of claim 1 , wherein selecting the destination language further comprises:
accessing a user profile; and
identifying, via the user profile, a user setting for the destination language.
8. The method of claim 1 , further comprising converting the multilingual query into a format that the computing device can process.
9. The method of claim 1 , wherein selecting the language associated with the computing device further comprises selecting a language of an operating system running on the computing device.
10. The method of claim 1 , wherein the generating for output the response to the multilingual query further comprises:
identifying, based on the natural language query, a content item; and
generating for output, at the computing device, the content item.
11. A system comprising:
input/output circuitry configured to:
receive, at a computing device, a multilingual query comprising at least a first source language and a second source language;
processing circuitry configured to:
select, based on a language associated with the computing device, a destination language;
for words of the multilingual query that are in a source language other than the destination language, translate, word for word, the words into the destination language to produce a monolingual query, wherein a word order of the multilingual query and a word order of the monolingual query are the same;
identify a trained network that has been trained on the first source language and the second source language;
input the monolingual query into the trained network to map the monolingual query to a natural language query in the destination language; and
generate for output, at the computing device and based on the natural language query, a response to the multilingual query.
12. The system of claim 11 , wherein the processing circuitry is further configured to perform at least one of the translating or the mapping the monolingual query to the natural language query in the destination language at the computing device.
13. The system of claim 11 , wherein the processing circuitry is further configured to enable the computing device to communicate with a server that performs at least one of the translating or the mapping the monolingual query to the natural language query in the destination language.
14. The system of claim 11 , wherein the processing circuitry is configured to map the monolingual query to the natural language query in the destination language is further configured to utilize the trained network, wherein the trained network comprises a hidden state based on a word order of the destination language.
15. The system of claim 11 , wherein the input/output circuitry configured to receive the multilingual query is further configured to receive the multilingual query comprising a spoken input or a text input.
16. The system of claim 11 , wherein the processing circuitry configured to select the destination language is further configured to select the language with one of a machine learning model or a neural network model.
17. The system of claim 11 , wherein the processing circuitry configured to select the destination language is further configured to:
access a user profile; and
identify, via the user profile, a user setting for the destination language.
18. The system of claim 11 , wherein the processing circuitry is further configured to convert the multilingual query into a format that the computing device can process.
19. The system of claim 11 , wherein the processing circuitry configured to select the language associated with the computing device is further configured to select a language of an operating system running on the computing device.
20. The system of claim 11 , wherein the processing circuitry configured to generate for output the response to the multilingual query is further configured to:
identify, based on the natural language query, a content item; and
generate for output, at the computing device, the content item.