Systems and methods for improving comprehension in translation based on context-based references
Methods and systems are disclosed herein for a context assistance system converting a reference in a content item based on context associated with the content item. For example, the context assistance system identifies a first entity referenced in the content item associated with a first context. The context assistance system then determines at least one attribute of the first entity. Next, the context assistance system identifies a second context in which the content item is to be presented. The context assistance system determines the second entity based on the second context and on the at least one attribute of the first entity. The context assistance system replaces reference to the first entity in the content item with reference to the second entity.
1 . A method comprising:
receiving, at a user device during output of a content item, a request to output the content item in a second context, wherein the content item is received in a first context and wherein the content item comprises a plurality of ordered portions having a first portion scheduled for output before a last portion of the content item is received;
identifying, in the first ordered portion of the plurality of ordered portions, a reference to a first entity associated with the first context;
determining a second entity associated with the second context by:
accessing, by the user device from a remote storage via a communications network, a knowledge graph stored in the remote storage, wherein a data structure of the knowledge graph comprises a plurality of entities and corresponding respective attribute information;
based on the respective attribute information of the first entity, selecting the second entity from the plurality of entities included in the data structure of the knowledge graph;
replacing the reference to the first entity in the first ordered portion with a reference to the second entity; and
generating for output, by an output device of the user device, the first ordered portion of the plurality of ordered portions including the reference to the second entity.
2 . The method of claim 1 , wherein:
the first entity is one of a plurality of referenced entities and the second entity is one of a plurality of replacement entities, the method further comprising:
replacing each reference to each referenced entity of the plurality of referenced entities with reference to a respective replacement entity of the plurality of replacement entities.
3 . The method of claim 1 , wherein the first ordered portion is one of a plurality of portions comprising reference to the first entity, the method further comprising:
replacing each reference to the first entity within each portion of the plurality of portions with the reference to the second entity.
4 . The method of claim 1 , further comprising:
receiving user preference information for a user associated with the user device, wherein the second context is identified based on the user preference information.
5 . The method of claim 1 , wherein determining the second entity associated with the second context further comprises:
based on the respective attribute information of the first entity, identifying a plurality of candidates from the plurality of entities for the second entity;
calculating a respective similarity score for each of the plurality of candidates; and
wherein the second entity is selected from the plurality of candidates based on the respective similarity score.
6 . The method of claim 5 , wherein calculating the respective similarity score comprises:
for each candidate of the plurality of candidates, comparing the at least one attribute of the first entity to a corresponding at least one attribute of each of the plurality of candidates; and
determining, based on the comparing, whether the at least one attribute of the first entity matches the at least one attribute of each of the plurality of candidates; and wherein the respective similarity score is calculated based on matches between the at least one attribute of the first entity and the at least one attribute of each of the plurality of candidates.
7 . The method of claim 5 , wherein calculating the respective similarity score comprises:
for each of the plurality of candidates, calculating a respective popularity score indicating a level of popularity based on entity information; and
wherein the respective similarity score is calculated based on the respective popularity score.
8 . The method of claim 5 , wherein calculating the respective similarity score comprises:
for each of the plurality of candidates, determining a respective weight indicating a level of association of a respective attribute with a respective entity based on the entity information; and
wherein the respective similarity score is calculated based on the determined weight.
9 . The method of claim 1 , further comprising:
subsequent to generating for output the first ordered portion of the plurality of ordered portions including the reference to the second entity, identifying, in a later ordered portion of the plurality of ordered portions, a reference to a third entity associated with the first context; and
replacing the reference to the third entity in the later ordered portion with a reference to a fourth entity.
10 . The method of claim 1 , wherein the first context and second context are both one of: a language, a culture, a country, a location, or a religion.
11 . A system comprising:
Input/Output (I/O) circuitry configured to:
receive, at a user device during output of a content item, a request to output the content item in a second context, wherein the content item is received in a first context and wherein the content item comprises a plurality of ordered portions having a first portion scheduled for output before a last portion of the content item is received;
control circuitry configured to:
identify, in the first ordered portion of the plurality of ordered portions, a reference to a first entity associated with the first context;
determine a second entity associated with the second context by:
accessing, by the user device from a remote storage via a communications network, a knowledge graph stored in the remote storage, wherein a data structure of the knowledge graph comprises a plurality of entities and corresponding respective attribute information;
based on the respective attribute information of the first entity, selecting the second entity from the plurality of entities included in the data structure of the knowledge graph;
replace the reference to the first entity in the first ordered portion with a reference to the second entity; and
wherein the I/O circuitry is further configured to:
generate for output, by an output device of the user device, the first ordered portion of the plurality of ordered portions including the reference to the second entity.
12 . The system of claim 11 , wherein:
the first entity is one of a plurality of referenced entities and the second entity is one of a plurality of replacement entities, wherein the control circuitry is further configured to:
replace each reference to each referenced entity of the plurality of referenced entities with reference to a respective replacement entity of the plurality of replacement entities.
13 . The system of claim 11 , wherein the first ordered portion is one of a plurality of portions comprising reference to the first entity, wherein the control circuitry is further configured to:
replace each reference to the first entity within each portion of the plurality of portions with the reference to the second entity.
14 . The system of claim 11 , wherein the control circuitry is further configured to:
receive user preference information for a user associated with the user device, wherein the second context is identified based on the user preference information.
15 . The system of claim 11 , wherein the control circuitry is further configured to determine the second entity associated with the second context by:
based on the respective attribute information of the first entity, identifying a plurality of candidates from the plurality of entities for the second entity;
calculating a respective similarity score for each of the plurality of candidates; and
wherein the second entity is selected from the plurality of candidates based on the respective similarity score.
16 . The system of claim 15 , wherein the control circuitry is further configured to calculate the respective similarity score by:
for each candidate of the plurality of candidates, comparing the at least one attribute of the first entity to a corresponding at least one attribute of each of the plurality of candidates; and
determining, based on the comparing, whether the at least one attribute of the first entity matches the at least one attribute of each of the plurality of candidates; and wherein the respective similarity score is calculated based on matches between the at least one attribute of the first entity and the at least one attribute of each of the plurality of candidates.
17 . The system of claim 15 , wherein the control circuitry is further configured to calculate the respective similarity score by:
for each of the plurality of candidates, calculating a respective popularity score indicating a level of popularity based on entity information; and
wherein the respective similarity score is calculated based on the respective popularity score.
18 . The system of claim 15 , wherein the control circuitry is further configured to calculate the respective similarity score by:
for each of the plurality of candidates, determining a respective weight indicating a level of association of a respective attribute with a respective entity based on the entity information; and
wherein the respective similarity score is calculated based on the determined weight.
19 . The system of claim 15 , wherein the control circuitry is further configured to:
subsequent to generating for output the first ordered portion of the plurality of ordered portions including the reference to the second entity, identify, in a later ordered portion of the plurality of ordered portions, a reference to a third entity associated with the first context; and
replace the reference to the third entity in the later ordered portion with a reference to a fourth entity.
20 . The system of claim 11 , wherein the first context and second context are both one of: a language, a culture, a country, a location, or a religion.