Navigating electronic documents using domain discourse trees

1. A computer-implemented method for navigating text using an extended discourse tree, the method comprising:

accessing an extended discourse tree representing a plurality of documents, wherein the extended discourse tree comprises a first discourse tree for a first document and a second discourse tree for a second document;

determining, from the extended discourse tree, (i) a first elementary discourse unit that is responsive to a query from a user device and (ii) a first position that corresponds to the first elementary discourse unit;

determining, from the extended discourse tree, a set of navigation options comprising (i) a first rhetorical relationship between the first elementary discourse unit and a second elementary discourse unit of the first discourse tree and (ii) a second rhetorical relationship between the first elementary discourse unit and a third elementary discourse unit of the second discourse tree;

presenting the first and second rhetorical relationships to a user device; and

responsive to (i) receiving, from a user device, a selection of the first rhetorical relationship, presenting the second elementary discourse unit to the user device, or (ii) receiving, from the user device, a selection of the second rhetorical relationship, presenting the third elementary discourse unit to the user device.

2. The computer-implemented method of claim 1 , wherein each of the first discourse tree and the second discourse tree comprises a plurality of nodes, wherein each nonterminal node of the plurality of nodes represents a rhetorical relationship, and wherein each terminal node of the nodes of the respective discourse tree is associated with an elementary discourse unit.

3. The computer-implemented method of claim 1 , further comprising responsive to receiving an additional query from the user device, determining an additional elementary discourse unit that is responsive to the additional query and presenting the additional elementary discourse unit to the user device.

4. The computer-implemented method of claim 1 , wherein determining the first elementary discourse unit further comprises identifying the first elementary discourse unit in the extended discourse tree and matching one or more keywords from the query in the first elementary discourse unit.

5. The computer-implemented method of claim 1 , wherein determining the first elementary discourse unit further comprises:

generating a first parse tree for the query;

generating additional parse trees for each of one or more elementary discourse units; and

responsive to determining that one of the additional parse trees includes the first parse tree, selecting the elementary discourse unit corresponding to the additional parse tree as the first elementary discourse unit.

6. The computer-implemented method of claim 1 , wherein each of the first and second rhetorical relationships are (i) elaboration, (ii) enablement, (iii) condition, (iv) contrast, or (v) attribution.

7. The computer-implemented method of claim 1 , wherein the first document comprises a first plurality of elementary discourse units, the first discourse tree represents a first rhetorical relationship between at least two of the first plurality of elementary discourse units, the second document comprises a second plurality of elementary discourse units, and the second discourse tree represents a second rhetorical relationship between at least two of the second plurality of elementary discourse units.

8. The computer-implemented method of claim 7 , wherein the extended discourse tree comprises a link representing by a rhetorical relationship between a common entity in the first discourse tree and the second discourse tree.

9. A system comprising:

a non-transitory computer-readable medium storing computer-executable program instructions; and

a processing device communicatively coupled to the non-transitory computer-readable medium for executing the computer-executable program instructions, wherein executing the computer-executable program instructions configures the processing device to perform operations comprising:

accessing an extended discourse tree representing a plurality of documents, wherein the extended discourse tree comprises a first discourse tree for a first document and a second discourse tree for a second document;

determining, from the extended discourse tree, (i) a first elementary discourse unit that is responsive to a query from a user device and (ii) a first position that corresponds to the first elementary discourse unit;

determining, from the extended discourse tree, a set of navigation options comprising (i) a first rhetorical relationship between the first elementary discourse unit and a second elementary discourse unit of the first discourse tree and (ii) a second rhetorical relationship between the first elementary discourse unit and a third elementary discourse unit of the second discourse tree;

presenting the first and second rhetorical relationships to a user device; and

responsive to (i) receiving, from a user device, a selection of the first rhetorical relationship, presenting the second elementary discourse unit to the user device, or (ii) receiving, from the user device, a selection of the second rhetorical relationship,

presenting the third elementary discourse unit to the user device.

10. The system of claim 9 , wherein the operations further comprise responsive to receiving, from the user device, an additional query, determining an additional elementary discourse unit that is responsive to the additional query and presenting the additional elementary discourse unit to the user device.

11. The system of claim 9 , wherein determining the first elementary discourse unit further comprises matching one or more keywords from the query in the first elementary discourse unit.

12. The system of claim 9 , wherein determining the first elementary discourse unit further comprises:

generating a first parse tree for the query;

generating additional parse trees for each of one or more elementary discourse units; and

responsive to determining that one of the additional parse trees includes the first parse tree, selecting the elementary discourse unit corresponding to the additional parse tree as the first elementary discourse unit.

13. The system of claim 9 , wherein each of the first and second rhetorical relationships are (i) elaboration, (ii) enablement, (iii) condition, (iv) contrast, or (v) attribution.

14. The system of claim 9 , wherein the first document comprises a first plurality of elementary discourse units, the first discourse tree represents a first rhetorical relationship between at least two of the first plurality of elementary discourse units, the second document comprises a second plurality of elementary discourse units, and the second discourse tree represents a second rhetorical relationship between at least two of the second plurality of elementary discourse units.

15. A non-transitory computer-readable medium storing computer-executable program instructions that when executed by a processor, perform operations comprising:

accessing an extended discourse tree representing a plurality of documents, wherein the extended discourse tree comprises a first discourse tree for a first document and a second discourse tree for a second document;

determining, from the extended discourse tree, (i) a first elementary discourse unit that is responsive to a query from a user device and (ii) a first position that corresponds to the first elementary discourse unit;

determining, from the extended discourse tree, a set of navigation options comprising (i) a first rhetorical relationship between the first elementary discourse unit and a second elementary discourse unit of the first discourse tree and (ii) a second rhetorical relationship between the first elementary discourse unit and a third elementary discourse unit of the second discourse tree;

presenting the first and second rhetorical relationships to a user device; and

responsive to (i) receiving, from a user device, a selection of the first rhetorical relationship, presenting the second elementary discourse unit to the user device, or (ii) receiving, from the user device, a selection of the second rhetorical relationship, presenting the third elementary discourse unit to the user device.

16. The non-transitory computer-readable medium of claim 15 , wherein the operations further comprise responsive to receiving, from the user device, an additional query, determining an additional elementary discourse unit that is responsive to the additional query and presenting the additional elementary discourse unit to the user device.

17. The non-transitory computer-readable medium of claim 15 , wherein

determining the first elementary discourse unit further comprises identifying the first elementary discourse unit in the extended discourse tree and matching one or more keywords from the query in the first elementary discourse unit.

18. The non-transitory computer-readable medium of claim 15 , wherein determining the first elementary discourse unit further comprises:

generating a first parse tree for the query;

generating additional parse trees for each of one or more elementary discourse units; and

responsive to determining that one of the additional parse trees includes the first parse tree, selecting the elementary discourse unit corresponding to the additional parse tree as the first elementary discourse unit.

19. The non-transitory computer-readable medium of claim 15 , wherein each of the first and second rhetorical relationships are (i) elaboration, (ii) enablement, (iii) condition, (iv) contrast, or (v) attribution.

20. The non-transitory computer-readable medium of claim 15 , wherein the extended discourse tree comprises a link representing a rhetorical relationship between a common entity in the first discourse tree and the second discourse tree.