Generating output for presentation in response to user interface input, where the input and/or the output include chatspeak

Patent metadata

Field	Value
Publication number	US-11238242-B2
Application number	US-201916360752-A
Country	US
Kind code	B2
Filing date	Mar 21, 2019
Priority date	May 17, 2016
Publication date	Feb 1, 2022
Grant date	Feb 1, 2022

Abstract

Some implementations are directed to translating chatspeak to a normalized form, where the chatspeak is included in natural language input formulated by a user via a user interface input device of a computing device—such as input provided by the user to an automated assistant. The normalized form of the chatspeak may be utilized by the automated assistant in determining reply content that is responsive to the natural language input, and that reply content may be presented to the user via one or more user interface output devices of the computing device of the user. Some implementations are additionally and/or alternatively directed to providing, for presentation to a user, natural language output that includes chatspeak in lieu of a normalized form of the chatspeak, based at least in part on a “chatspeak measure” that is determined based on past usage of chatspeak by the user and/or by additional users.

First claim

What is claimed is:

1. A method implemented by one or more processors, comprising:
determining a chatspeak measure for one or more users based on a plurality of messages contributed to message exchange threads by one or more of the users;
receiving natural language input submitted by a user of the users as part of an ongoing message exchange thread between at least the user and an automated assistant, the natural language input being formulated by the user via a user interface input device of a computing device of the user;
generating natural language output for inclusion in a response of the automated assistant to the natural language input, wherein generating the natural language output comprises incorporating one or more chatspeak terms into the natural language output based on the chatspeak measure; and
incorporating the response of the automated assistant into the message exchange thread, the response including the natural language output with the one or more chatspeak terms.

2. The method of claim 1 , wherein incorporating the response into the message exchange thread comprises inserting the response into a transcript of the message exchange thread that is displayed in a graphical user interface of a message exchange client operating on the computing device of the user.

3. The method of claim 1 , wherein the chatspeak measure is specific to a group of one or more chatspeak terms that includes at least the chatspeak terms included in the natural language output, and wherein incorporating the one or more chatspeak terms into the natural language output is based on the chatspeak measure being specific to the group that includes the chatspeak terms.

4. The method of claim 1 , wherein incorporating the chatspeak terms into the natural language output comprises:
identifying initial natural language output that is responsive to the natural language input;
determining that one or more given terms of the initial natural language output map to the chatspeak terms; and
replacing the given terms of the initial natural language output with the chatspeak terms.

5. The method of claim 1 , further comprising:
determining an additional chatspeak measure for one or more of the users;
wherein generating the natural language output comprises incorporating one or more of the chatspeak terms into the natural language output based on the chatspeak measure and based on the additional chatspeak measure.

6. The method of claim 5 , wherein the chatspeak measure is specific to the user and is applicable to a plurality of chatspeak terms, including one or more additional chatspeak terms not incorporated into the natural language output; and wherein the additional chatspeak measure is not specific to the user and is specific to at least one of the chatspeak terms incorporated into the natural language output.

7. The method of claim 1 , wherein the chatspeak measure is specific to the user.

8. The method of claim 7 , wherein the message exchange threads include past automated assistant message exchange threads between at least the user and the automated assistant.

9. The method of claim 8 , wherein determining the chatspeak measure is based on a count of instances where chatspeak was utilized in the messages and further comprising determining one of the instances on which the count is based, wherein determining the one of the instances comprises:
receiving a given message of the messages in one of the past automated assistant message exchange threads, the given message being formulated by the user and including at least a first term and a second term;
identifying, for at least the first term of the natural language input, a first normalization of the first term;
generating a candidate alternate input for the natural language input, the generating comprising replacing the first term with the first normalization and including, in the candidate alternate input, either the second term or a second normalization of the second term;
determining a first score for the natural language input;
determining a second score for the candidate alternate input;
selecting the candidate alternate input based on the first score and the second score;
determining reply content based on the candidate alternate input;
incorporating the reply content into the one of the past automated assistant message exchange threads as a response to the natural language input by the automated assistant, wherein incorporating the reply content is based on selecting the candidate alternate input; and
storing an indication of the one of the instances based on selecting the candidate alternate input.

10. The method of claim 9 , wherein determining the first score for the natural language input is based on applying at least the first term and the second term to a language model and wherein determining the second score for the candidate alternate input based on applying at least the first normalization and either the second term or the second normalization to the language model.

11. The method of claim 9 , wherein the chatspeak measure is specific to the user and is specific to the chatspeak terms; and wherein storing the indication of the one of the instances based on selecting the candidate alternate input further comprises:
storing an association of the indication to at least the first term or the first normalization.

12. The method of claim 1 , wherein determining the chatspeak measure is based on at least one basis selected from the group consisting of: a count of instances where chatspeak was utilized in the messages, a quality of one or more chatspeak terms used in the messages, commonness of the chatspeak terms, and consistency of use of the chatspeak terms.

13. A system, comprising:
memory storing instructions;
one or more processors executing the instructions stored in the memory to cause the one or more processors to:
determine a chatspeak measure for one or more users based on a plurality of messages contributed to message exchange threads by one or more of the users;
receive natural language input submitted by a user of the users as part of an ongoing message exchange thread between at least the user and an automated assistant, the natural language input being formulated by the user via a user interface input device of a computing device of the user;
generate natural language output for inclusion in a response of the automated assistant to the natural language input, wherein in generating the natural language output one or more of the processors are to incorporate one or more chatspeak terms into the natural language output based on the chatspeak measure; and
incorporate the response of the automated assistant into the message exchange thread, the response including the natural language output with the one or more chatspeak terms.

14. The system of claim 13 , wherein in incorporating the response into the message exchange thread one or more of the processors are to insert the response into a transcript of the message exchange thread that is displayed in a graphical user interface of a message exchange client operating on the computing device of the user.

15. The system of claim 13 , wherein the chatspeak measure is specific to a group of one or more chatspeak terms that includes at least the chatspeak terms included in the natural language output, and wherein incorporating the one or more chatspeak terms into the natural language output is based on the chatspeak measure being specific to the group that includes the chatspeak terms.

16. The system of claim 13 , wherein in incorporating the chatspeak terms into the natural langua

Assignees

• Google Llc

Inventors

• Quah Wan Fen Nicole
• Horling Bryan
• Garrett Maryam
• Roark Brian
• Sproat Richard

Classifications

• H04L51/02 Primary

  using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages · CPC title

• H04L51/216

  Handling conversation history, e.g. grouping of messages in sessions or threads · CPC title

• H04L51/046 Primary

  Interoperability with other network applications or services · CPC title

• H04L51/04

  Real-time or near real-time messaging, e.g. instant messaging [IM] · CPC title

• G06F40/56

  Natural language generation · CPC title