Search query generation based upon received text

1. A method, comprising:

displaying a content item creation interface via a client device;

receiving, via the content item creation interface, a first set of content item text;

selecting, based upon the first set of content item text and a plurality of sets of content item text associated with a plurality of content items, a set of content items from among the plurality of content items;

determining, based upon the first set of content item text and the set of content items, a set of terms;

generating a similarity profile associated with the set of terms, wherein the similarity profile is indicative of similarity scores associated with similarities between terms of the set of terms;

determining, based upon the similarity profile, relevance scores associated with the set of terms;

selecting, based upon the relevance scores, one or more search terms from among the set of terms;

performing, based upon the one or more search terms, an image search using an image database;

displaying, via the content item creation interface, a set of search results of the image search;

receiving, via the content item creation interface, a selection of an image of a plurality of images in the set of search results;

responsive to the selection of the image, combining at least a portion of the image with the first set of content item text received via the content item creation interface to generate a content item; and

presenting the generated content item to one or more other client devices.

2. The method of claim 1 , comprising:

determining, based upon the first set of content item text and the plurality of sets of content item text associated with the plurality of content items, a plurality of similarity scores associated with the plurality of sets of content item text, wherein:

the plurality of sets of content item text comprises a second set of content item text of a first content item of the plurality of content items; and

a first similarity score of the plurality of similarity scores is associated with a similarity between the first set of content item text and the second set of content item text; and

selecting the set of content items from among the plurality of content items is based upon the plurality of similarity scores.

3. The method of claim 2 , wherein:

selecting the set of content items from among the plurality of content items is based upon a determination that the set of content items are associated with highest similarity scores of the plurality of similarity scores.

4. The method of claim 2 , comprising:

determining a first embedding-based representation of the first set of content item text, wherein the determining the plurality of similarity scores comprises determining the first similarity score based upon the first embedding-based representation and a second embedding-based representation of the second set of content item text of the first content item.

5. The method of claim 1 , comprising:

determining embedding-based representations of the set of terms, wherein the similarity scores indicated by the similarity profile are based upon the embedding-based representations.

6. The method of claim 1 , comprising:

analyzing the first set of content item text to identify one or more terms in the first set of content item text, wherein the one or more terms are included in the set of terms.

7. The method of claim 1 , comprising:

translating the first set of content item text in a first language to a translated set of content item text in a second language; and

analyzing the translated set of content item text to identify one or more terms in the translated set of content item text, wherein the one or more terms are included in the set of terms.

8. The method of claim 1 , comprising:

analyzing an image of a first content item of the set of content items to determine one or more object terms of one or more objects in the image, wherein the one or more object terms are included in the set of terms.

9. The method of claim 1 , comprising:

analyzing sets of content item text associated with content items of the set of content items to identify one or more terms in the sets of content item text, wherein the one or more terms are included in the set of terms.

10. The method of claim 1 , comprising:

determining, based upon a term of the set of terms and a content item category associated with the first set of content item text, a category bias associated with the term, wherein determining the relevance scores comprises determining a relevance score associated with the term based upon the category bias.

11. The method of claim 1 , comprising:

determining embedding-based representations, of the set of terms, comprising:

a first embedding-based representation of a first term of the set of terms;

a second embedding-based representation of a second term of the set of terms; and

a third embedding-based representation of a third term of the set of terms;

determining a first measure of similarity between the first embedding-based representation and the second embedding-based representation; and

determining a second measure of similarity between the first embedding-based representation and the third embedding-based representation.

12. The method of claim 11 , comprising:

determining, for inclusion in the similarity profile, a first similarity score associated with a similarity between the first term and the second term based upon the first measure of similarity; and

determining, for inclusion in the similarity profile, a second similarity score associated with a similarity between the first term and the third term based upon the second measure of similarity.

13. A computing device comprising:

a processor; and

memory comprising processor-executable instructions that when executed by the processor cause performance of operations, the operations comprising:

receiving, from a client device, a first set of text;

selecting, based upon the first set of text and a plurality of sets of content item text associated with a plurality of content items, a set of content items from among the plurality of content items;

determining, based upon the first set of text and the set of content items, a set of terms;

generating a similarity profile associated with the set of terms, wherein the similarity profile is indicative of similarity scores associated with similarities between terms of the set of terms;

determining, based upon the similarity profile, relevance scores associated with the set of terms;

selecting, based upon the relevance scores, one or more search terms from among the set of terms;

performing a search based upon the one or more search terms;

sending, to the client device, a set of search results of the search;

receiving, from the client device, a selection of an image of a plurality of images in the set of search results;

responsive to the selection of the image, combining at least a portion of the image with the first set of text to generate a content item; and

at least one of presenting the generated content item to one or more other client devices or determining a target audience for the generated content item.

14. The computing device of claim 13 , the operations comprising:

determining, based upon the first set of text and the plurality of sets of content item text associated with the plurality of content items, a plurality of similarity scores associated with the plurality of sets of content item text, wherein:

the plurality of sets of content item text comprises a first set of content item text of a first content item of the plurality of content items; and

a first similarity score of the plurality of similarity scores is associated with a similarity between the first set of text and the first set of content item text; and

selecting the set of content items from among the plurality of content items is based upon the plurality of similarity scores.

15. The computing device of claim 14 , wherein:

selecting the set of content items from among the plurality of content items is based upon a determination that the set of content items are associated with highest similarity scores of the plurality of similarity scores.

16. The computing device of claim 13 , the operations comprising:

determining embedding-based representations of the set of terms, wherein the similarity scores indicated by the similarity profile are based upon the embedding-based representations.

17. The computing device of claim 13 , the operations comprising:

analyzing the first set of text to identify one or more terms in the first set of text, wherein the one or more terms are included in the set of terms.

18. The computing device of claim 13 , the operations comprising:

translating the first set of text in a first language to a translated set of content item text in a second language; and

analyzing the translated set of content item text to identify one or more terms in the translated set of content item text, wherein the one or more terms are included in the set of terms.

19. The computing device of claim 13 , the operations comprising:

analyzing an image of a first content item of the set of content items to determine one or more object terms of one or more objects in the image, wherein the one or more object terms are included in the set of terms; and

analyzing sets of content item text associated with content items of the set of content items to identify one or more terms in the sets of content item text, wherein the one or more terms are included in the set of terms.

20. A non-transitory machine readable medium having stored thereon processor-executable instructions that when executed cause performance of operations, the operations comprising:

displaying a content item creation interface via a client device;

receiving, via the content item creation interface, a first set of content item text;

selecting, based upon the first set of content item text and a plurality of sets of content item text associated with a plurality of content items, a set of content items from among the plurality of content items;

determining, based upon the first set of content item text and the set of content items, a set of terms;

determining embedding-based representations, of the set of terms, comprising:

a first embedding-based representation of a first term of the set of terms;

a second embedding-based representation of a second term of the set of terms; and

a third embedding-based representation of a third term of the set of terms;

determining a first measure of similarity between the first embedding-based representation and the second embedding-based representation;

determining a second measure of similarity between the first embedding-based representation and the third embedding-based representation;

generating, based upon the first measure of similarity and the second measure of similarity, a similarity profile associated with the set of terms, wherein the similarity profile is indicative of similarity scores associated with similarities between terms of the set of terms;

determining, based upon the similarity profile, relevance scores associated with the set of terms;

selecting, based upon the relevance scores, one or more search terms from among the set of terms;

performing, based upon the one or more search terms, an image search using an image database;

displaying, via the content item creation interface, a set of search results of the image search;

receiving, via the content item creation interface, a selection of an image of a plurality of images in the set of search results; and

responsive to the selection of the image, combining at least a portion of the image with the first set of content item text to generate a content item.