Methods and servers for ranking digital documents in response to a query

1. A method of ranking digital documents in response to a query, the digital documents being potentially relevant to the query having a first term and a second term, the query having been submitted by a user of an electronic device communicatively coupled with a server hosting a search engine, the search engine being associated with an inverted index storing information associated with document-term (DT) pairs, the method executable by the server, the method comprising:

for a given document from a plurality of potentially relevant documents:

accessing the inverted index for retrieving query-independent data for a first DT pair and a second DT pair, the first DT pair having the given document and the first term, the second DT pair having the given document and the second term,

the query-independent data being indicative of (i) a term-specific occurrence of the first term in content associated with the given document and (ii) a term-specific occurrence of the second term in the content associated with the given document;

generating a query-dependent feature using the query-independent data retrieved for the first DT pair and the second DT pair,

the query-dependent feature being indicative of a group occurrence of the first term with the second term in the content associated with the given document;

generating a ranking feature for the given document based on at least the first term, the second term, and the query-dependent feature, in which the ranking feature for the given document is performed by a Neural Network (NN); and

ranking the given document from the plurality of potentially relevant documents based on at least the ranking feature,

wherein, the server trains the NN to generate the ranking feature by generating a training set for a training document-query (DQ) pair to be used during a given training iteration of the NN, the training DQ pair having a training query and a training document, the training document being associated with a label, the label being indicative of relevance of the training document to the training query, the generating comprising:

generating, by the server, a plurality of training term embeddings based on respective terms from the training query;

accessing the inverted index associated with the search engine for retrieving a plurality of query-independent datasets associated with respective ones of a plurality of training DT pairs,

a given one of the plurality of training DT pairs including the training document and a respective one of the plurality of terms from the training query;

generating a plurality of training feature vectors for the plurality of training DT pairs using the plurality of query-independent datasets;

concatenating the plurality of training term embeddings with the plurality of training feature vectors to generate a concatenated input;

during a given training iteration of the NN:

inputting, into the NN, the concatenated input for generating a predicted ranking feature for the training DQ pair; and

adjusting the NN based on a comparison between the label and the predicted ranking feature so that the NN generates for a given in-use DQ pair a respective predicted ranking feature that is indicative of relevance of a respective in-use document to a respective in-use query.

2. The method of claim 1 , wherein the query-independent data has been stored in the inverted index prior to receipt of the query from the electronic device, and wherein the query-dependent feature is generated after the receipt of the query from the electronic device.

3. The method of claim 1 , wherein the query-dependent feature is generated using the query-independent data in real-time during a document ranking procedure of the search engine.

4. The method of claim 1 , wherein the ranking is performed by a decision-tree-based Machine Learning Algorithm (MLA) configured to rank the plurality of potentially relevant documents based on their relevance to the query.

5. The method of claim 1 , wherein the method further comprises, for a given one of the plurality of terms, determining a similar term, and wherein:

when accessing the inverted index for retrieving the query-independent data, the retrieved query-independent data comprises query-independent data for a third DT pair, the third DT pair having the given document and the similar term.

6. The method of claim 1 , wherein the accessing the inverted index is for further retrieving a query-independent content-based data associated with the first DT pair and the second DT pair,

the query-independent content-based data being indicative of a textual context of the respective term within the content associated with the given document.

7. The method of claim 1 , wherein the term-specific occurrence of the first term comprises at least one of:

one or more positions of the first term in a title associated with given document;

one or more positions of the first term in a URL associated with the given document; and

one or more positions of the first term in a body of the given document.

8. The method of claim 1 , wherein the group occurrence of the first term with the second term in the content associated with the given document comprises at least one of:

a number of times the second term from the query is included in addition to the first term in a title associated with the given document;

a number of times the second term from the query is included in addition to the first term in a URL associated with the given document; and

a number of times the second term from the query is included in addition to the first term in a body of the given document.

9. A server for ranking digital documents in response to a query, the digital documents being potentially relevant to the query having a first term and a second term, the query having been submitted by a user of an electronic device communicatively coupled with the server hosting a search engine, the search engine being associated with an inverted index storing information associated with document-term (DT) pairs, the server, comprising hardware, configured to:

for a given document from a plurality of potentially relevant documents:

access the inverted index for retrieving query-independent data for a first DT pair and a second DT pair, the first DT pair having the given document and the first term, the second DT pair having the given document and the second term,

the query-independent data being indicative of (i) a term-specific occurrence of the first term in content associated with the given document and (ii) a term-specific occurrence of the second term in the content associated with the given document;

generate a query-dependent feature using the query-independent data retrieved for the first DT pair and the second DT pair,

the query-dependent feature being indicative of a group occurrence of the first term with the second term in the content associated with the given document; generate a ranking feature for the given document based on at least the first term, the second term, and the query-dependent feature, in which the server incorporates a Neural Network (NN) to generate the ranking feature for the given document; and

rank the given document from the plurality of potentially relevant documents based on at least the ranking feature,

wherein the server is further configured to train the NN to generate the ranking feature by generating a training set for a training document-query (DQ) pair to be used during a given training iteration of the NN, the training DQ pair having a training query and a training document, the training document being associated with a label, the label being indicative of relevance of the training document to the training query to generate the training set, the server being configured to:

generate a plurality of training term embeddings based on respective terms from the training query;

access the inverted index associated with the search engine for retrieving a plurality of query-independent datasets associated with respective ones of a plurality of training DT pairs,

a given one of the plurality of training DT pairs including the training document and a respective one of the plurality of terms from the training query;

concatenate the plurality of training term embeddings with the plurality of training feature vectors to generate a concatenated input;

during a given training iteration of the NN:

input, into the NN, the concatenated input for generating a predicted ranking feature for the training DO pair; and

adjust the NN based on a comparison between the label and the predicted ranking feature so that the NN generates for a given in-use DQ pair a respective predicted ranking feature that is indicative of relevance of a respective in-use document to a respective in-use query.

10. The server of claim 9 , wherein the query-independent data has been stored in the inverted index prior to receipt of the query from the electronic device, and wherein the query-dependent feature is generated after the receipt of the query from the electronic device.

11. The server of claim 9 , wherein the query-dependent feature is generated using the query-independent data in real-time during a document ranking procedure of the search engine.

12. The server of claim 9 , wherein the server is configured to rank by employing a decision-tree-based Machine Learning Algorithm (MLA) configured to rank the plurality of potentially relevant documents based on their relevance to the query.

13. The server of claim 9 , wherein the server is further configured to, for a given one of the plurality of terms, determine a similar term, and wherein:

when accessing the inverted index for retrieving the query-independent data, the retrieved query-independent data comprises query-independent data for a third DT pair, the third DT pair having the given document and the similar term.

14. The server of claim 9 , wherein the server is configured to access the inverted index for further retrieving a query-independent content-based data associated with the first DT pair and the second DT pair,

the query-independent content-based data being indicative of a textual context of the respective term within the content associated with the given document.

15. The server of claim 9 , wherein the term-specific occurrence of the first term comprises at least one of:

one or more positions of the first term in a title associated with given document;

one or more positions of the first term in a URL associated with the given document; and

one or more positions of the first term in a body of the given document.

16. The server of claims 9 , wherein the group occurrence of the first term with the second term in the content associated with the given document comprises at least one of:

a number of times the second term from the query is included in addition to the first term in a title associated with the given document;

a number of times the second term from the query is included in addition to the first term in a URL associated with the given document; and

a number of times the second term from the query is included in addition to the first term in a body of the given document.