Systems and methods for inserting dialogue into a query response
Systems and methods are described herein for inserting dialogue into query responses by generating and using dialogue metadata in conjunction with response templates. Metadata for each portion of dialogue of a plurality of portions of dialogue from a number of content items is stored, including information regarding the source content item, a transcript of the dialogue, and grammatical information. Upon receiving a query related to a content item, a type of response is first determined. Based on the type of response, and using the dialogue metadata, a portion of dialogue is identified for insertion into the response. The identified portion of dialogue is retrieved and inserted at an appropriate position within the response. The response is then generated for output.
1. A method comprising:
receiving a query;
determining a response to the query;
determining whether the query is related to a media content item;
in response to determining that the query is related to the media content item, identifying a portion of the media content item; and
inserting the identified portion of the media content item into the response, wherein the identified portion includes at least one of an exclamation based on the media content item, dialogue related to a specific character based on the media content item, or dialogue related to and based on the specific media content item.
2. The method of claim 1 , wherein the identifying the portion of the media content item comprises:
identifying a part of speech to be inserted into the response;
determining, using natural language processing, whether the portion of the content item includes the identified part of speech;
in response to determining that the portion of the media content item includes the identified part of speech, selecting the portion of the media content item; and
in response to determining that no portion of the media content item includes the identified part of speech:
selecting the portion of the media content item; and
modifying the selected portion of the media content item to include the identified part of speech.
3. The method of claim 1 , wherein the identifying the portion of the media content item comprises:
retrieving metadata of the portion of the media content item;
comparing the metadata of the portion of the media content item with a type of response to the query; and
selecting, based on the comparing, the portion of the media content item.
4. The method of claim 1 , further comprising:
retrieving a response template corresponding to a type of response to the query;
determining, using natural language processing, whether the category of the portion of the media content item can be inserted into the response template; and
in response to determining that the category of the portion of the media content item can be inserted into the response template, selecting the portion of the media content item.
5. The method of claim 1 , wherein the query is related to an entity within the media content item, the method further comprising:
identifying the entity, wherein an identified portion of the media content item corresponds to the entity;
retrieving a response template corresponding to a type of response to the query;
determining, using natural language processing, whether the identified portion of the media content item can be grammatically inserted into the response template; and
in response to determining that the identified portion of the media content item cannot be grammatically inserted into the response template, replacing proper nouns and pronouns within the identified portion of the media item with appropriate pronouns.
6. The method of claim 1 , further comprising:
comparing words of the identified portion of the media content item with words of a response template corresponding to a type of response to the query;
determining, based on the comparing, whether the identified portion of the media content item contains a contiguous set of words that is also contained in the response template; and
in response to determining that the identified portion of the media content item contains the contiguous set of words that is also contained in the response template, replacing a portion of the response template with the identified portion of the media content item.
7. The method of claim 1 , further comprising:
determining, based on the query, a type of response to the query,
wherein the inserting the identified portion of the media content item into the response is based on the type of response to the query.
8. The method of claim 1 , further comprising:
generating the response for output, wherein the response includes at least one of an acknowledgment, a generic answer, or one or more search results.
9. The method of claim 1 , wherein the response further includes the inserted identified portion, and
wherein the response including the inserted identified portion is more engaging than the response including the response prior to including the inserted identified portion.
10. The method of claim 1 , wherein each portion of the media content item comprises at least one of a portion of a book, a play, a show, or a movie; or a famous line of a famous creative work.
11. A system comprising:
memory; and
control circuitry configured to:
receive a query;
determine a response to the query;
determine whether the query is related to a media content item;
in response to determining that the query is related to the media content item, identify a portion of the media content item; and
insert the identified portion of the media content item into the response, wherein the identified portion includes at least one of an exclamation based on the media content item, dialogue related to a specific character based on the media content item, or dialogue related to and based on the specific media content item.
12. The system of claim 11 , wherein the control circuitry configured to identify the portion of the media content item is further configured to:
identify a part of speech to be inserted into the response;
determine, using natural language processing, whether the portion of the media content item includes the identified part of speech;
in response to determining that the portion of the media content item includes the identified part of speech, select the portion of the media content item; and
in response to determining that no portion of the media content item includes the identified part of speech:
select the portion of the media content item; and
modify the selected portion of the media content item to include the identified part of speech.
13. The system of claim 11 , wherein the control circuitry configured to identify the portion of the media content item is further configured to:
retrieve metadata of the portion of the media content item;
compare the metadata of the portion of the media content item with a type of response to the query; and
select, based on the comparing, the portion of the media content item.
14. The system of claim 11 , wherein the control circuitry is further configured to:
retrieve a response template corresponding to a type of response to the query;
determine, using natural language processing, whether the category of the portion of the media content item can be inserted into the response template; and
in response to determining that the category of the portion of the media content item can be inserted into the response template, select the portion of the media content item.
15. The system of claim 11 , wherein the query is related to an entity within the media content item, and wherein the control circuitry is further configured to:
identify the entity, wherein an identified portion of the media content item corresponds to the entity;
retrieve a response template corresponding to a type of response to the query;
determine, using natural language processing, whether the identified portion of the media content item can be grammatically inserted into the response template; and
in response to determining that the identified portion of the media content item cannot be grammatically inserted into the response template, replace proper nouns within the identified portion of the media content item with appropriate pronouns.
16. The system of claim 11 , wherein the control circuitry is further configured to:
compare words of the identified portion of the media content item with words of a response template corresponding to a type of response to the query;
determine, based on the comparing, whether the identified portion of the media content item contains a contiguous set of words that is also contained in the response template; and
in response to determining that the identified portion of the media content item contains the contiguous set of words that is also contained in the response template, replace a portion of the response template with the identified portion of the media content item.
17. The system of claim 11 , wherein the control circuitry is further configured to:
determine, based on the query, a type of response to the query,
wherein the inserting the identified portion of the media content item into the response is based on the type of response to the query.
18. The system of claim 11 , wherein the control circuitry is further configured to:
generate the response for output, wherein the response includes at least one of an acknowledgment, a generic answer, or one or more search results.
19. The system of claim 11 , wherein the response further includes the inserted identified portion, and
wherein the response including the inserted identified portion is more engaging than the response including the response prior to including the inserted identified portion.
20. The system of claim 11 , wherein each portion of the media content item comprises at least one of a portion of a book, a play, a show, or a movie; or a famous line of a famous creative work.