Method and system for entity recognition in a query

1. A method, implemented on at least one computing device each of which has at least one processor, storage, and a communication platform connected to a network for entity recognition in a query, the method comprising the steps of:

obtaining, by the at least one processor, an index that associates an alias with one or more entities, wherein each of the one or more entities is associated with one or more first features;

receiving, by the at least one processor, a query from a user, wherein the query is associated with one or more second features;

identifying, by the at least one processor, the alias in the query;

determining, by the at least one processor, whether the alias is associated with a single entity or with two or more entities according to the index;

responsive to a determination that the alias is associated with the single entity, selecting, by the at least one processor, the single entity;

responsive to a determination that the alias is associated with the two or more entities, selecting, by the at least one processor, at least one of the two or more entities based, at least in part, on the one or more first features associated with each of the two or more entities and the one or more second features associated with the query; and

providing, by the at least one processor, a search result to the user based on the selected single entity or the selected at least one of the two or more entities.

2. The method of claim 1 , wherein the index is obtained from a plurality of indices, each of which is generated offline by mapping a respective alias with entities across a plurality of domains.

3. The method of claim 1 , wherein the one or more second features associated with the query include at least one of:

features extracted based on information of the user; and

features extracted based on context of the query.

4. The method of claim 1 , wherein the selecting the at least one of the two or more entities comprises:

filtering the two or more entities based on their respective first features; and

ranking the filtered two or more entities based on relevance between their respective one or more first features and the one or more second features associated with the query.

5. The method of claim 4 , wherein the ranking the filtered two or more entities is performed based on a model that is trained based on at least one of user feedback and editorial labeling.

6. The method of claim 1 , wherein when the alias is associated with two or more entities according to the index, the at least one of the two or more entities is selected based, at least in part, on popularity of each of the two or more entities in a search history.

7. A system having at least one processor, storage, and a communication platform for entity recognition in a query, the system comprising:

an indexing module, implemented on the at least one processor and configured to obtain an index that associates an alias with one or more entities, wherein each of the one or more entities is associated with one or more first features;

a tokenizing unit, implemented on the at least one processor and configured to receive a query from a user, wherein the query is associated with one or more second features;

an identifying unit, implemented on the at least one processor and configured to identify the alias in the query;

a determining unit, implemented on the at least one processor and configured to:

determine whether the alias is associated with a single entity or with two or more entities according to the index;

responsive to a determination that the alias is associated with the single entity, select the single entity; and

responsive to a determination that the alias is associated with the two or more entities, select at least one of the two or more entities based, at least in part, on the one or more first features associated with each of the two or more entities and the one or more second features associated with the query; and

a search engine, implemented on the at least one processor and configured to provide a search result to the user based on the selected single entity or the selected at least one of the two or more entities.

8. The system of claim 7 , wherein the index is obtained from a plurality of indices, each of which is generated offline by mapping a respective alias with entities across a plurality of domains.

9. The system of claim 7 , wherein the one or more second features associated with the query include at least one of:

features extracted based on information of the user; and

features extracted based on context of the query.

10. The system of claim 7 , wherein the determining unit comprises:

filtering logic configured to filter the two or more entities based on their respective first features; and

ranking logic configured to rank the filtered two or more entities based on relevance between their respective one or more first features and the one or more second features associated with the query.

11. The system of claim 10 , wherein ranking the filtered two or more entities is performed based on a model that is trained based on at least one of user feedback and editorial labeling.

12. The system of claim 7 , wherein when the alias is associated with two or more entities according to the index, the at least one of the two or more entities is selected based, at least in part, on popularity of each of the two or more entities in a search history.

13. A non-transitory machine-readable medium having information recorded thereon for entity recognition in a query, wherein the information, when read by the machine, causes the machine to perform the following:

obtaining, by at least one processor, an index that associates an alias with one or more entities, wherein each of the one or more entities is associated with one or more first features;

receiving, by the at least one processor, a query from a user, wherein the query is associated with one or more second features;

identifying, by the at least one processor, the alias in the query;

determining, by the at least one processor, whether the alias is associated with a single entity or with two or more entities according to the index;

responsive to a determination that the alias is associated with the single entity, selecting, by the at least one processor, the single entity;

responsive to a determination that the alias is associated with the two or more entities, selecting, by the at least one processor, at least one of the two or more entities based, at least in part, on the one or more first features associated with each of the two or more entities and the one or more second features associated with the query; and

providing, by the at least one processor, a search result to the user based on the selected single entity or the selected at least one of the two or more entities.

14. The medium of claim 13 , wherein the index is obtained from a plurality of indices, each of which is generated offline by mapping a respective alias with entities across a plurality of domains.

15. The medium of claim 13 , wherein the one or more second features associated with the query include at least one of:

features extracted based on information of the user; and

features extracted based on context of the query.

16. The medium of claim 13 , wherein the selecting the at least one of the two or more entities comprises:

filtering the two or more entities based on their respective first features; and

ranking the filtered two or more entities based on relevance between their respective one or more first features and the one or more second features associated with the query.

17. The medium of claim 13 , wherein when the alias is associated with two or more entities according to the index, the at least one of the two or more entities is selected based, at least in part, on popularity of each of the two or more entities in a search history.