System and method for teaching writing using microanalysis of text

• US 7,013,259 B1
• Filed: 06/30/2000
• Issued: 03/14/2006
• Est. Priority Date: 06/30/2000
• Status: Active Grant

• Current Assignee: Fujifilm Business Innovation Corp. (Fujifilm Holdings Corporation)
• Original Assignee: Fuji Xerox Company Limited (Xerox Holdings Corp.)
• Inventors: Liew, Bee Yian, Van Den Berg, Martin Henk, Polanyi, Livia
• Primary Examiner(s): Knepper, David D.
• Assistant Examiner(s): Han, Qi
• Application Number:
  US09/609,325
• Time in Patent Office: 2,083 Days
• Field of Search: 704 1- 10
• US Class Current: 704/7
• CPC Class Codes: G06F 16/345 Summarisation for human users
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G09B 11/00 Teaching hand-writing, shorthand, drawing, or painting
• CPC Class Codes: G09B 5/02 with visual presentation of the material to be studied, e.g. using film strip

Abstract

A technique for teaching expository writing using a system that provides an objective reader centric microanalysis of the information a writer has conveyed to a virtual reader. The technique uses a theory of discourse analysis such as the Linguistic Discourse Model. Using the technique, a text is segmented into discrete units of meaning of the selected theoretic model. Student analysis and understanding are facilitated by the assignment of types to the discrete units of meaning and by linking the discrete units of meaning into a discourse tree under the constraints imposed by the selected theory. A virtual, or objective, reader centric summary of the information actually conveyed by the text is then compared to the writer designated important concepts and the results conveyed as feedback to the writer.

Claims

1. A method for teaching expository writing, comprising:

selecting a theory of discourse analysis for teaching writing;

segmenting a text into at least one text building units based on the selected theory of discourse;

analyzing each text building unit according to the selected theory of discourse;

wherein the selected theory of discourse analysis is selected from the list of at least Discourse Structures Theory, Linguistic Discourse Model, Rhetorical Structure Theory, Systemic Functional Grammar, and Tagmemics.

2. The method of claim 1, wherein the at least one text building units are combined into a structural representation of discourse consistent with the selected theory of discourse.

3. The method of claim 1, wherein the structural representation of discourse is a tree, and wherein the segmenting is performed automatically, and the structural representation is displayed.

4. The method of claim 1, further comprising displaying the segmented text.

5. The method of claim 1, further comprising displaying the analyzed text.

6. The method of claim 2, further comprising displaying the structural representation of discourse.

7. The method of claim 1, further comprising identifying user designated important concepts in the text.

8. The method of claim 1, further comprising generating a summary of text based on the selected theory of discourse.

9. The method of claim 8, further comprising determining coverage of user designated important concepts.

10. The method of claim 9, wherein determining coverage compares user designated concepts to the summary.

11. The method of claim 8, wherein summary generation comprises the following steps:

identifying the root node and assigning it a rank; and

recursively selecting each remaining child node;

for each child node that is a coordination node or a binary node assigning the child node the rank of the parent; and

for each child node that is a subordination node;

assigning to the subordinating node, the rank of the parent; and

assigning to the subordinated node, the rank of the parent incremented by 1.

12. The method of claim 8, wherein a summary is displayed by:

selecting a summary level p for a structural representation of discourse having a lowest level m and a highest level n so that m≦

p≦

n;

walking the nodes of the tree in order of insertion up to the level p; and

displaying the nodes traversed.

13. The method of claim 1, wherein the segmenting is performed automatically.

14. The method of claim 1, wherein the analysis is performed automatically.

15. A system for teaching expository writing, comprising:

an input device;

a display device;

a memory;

a segmenting circuit;

an analyzing circuit; and

a controller that selects a theory of discourse from the input device, segments a text received form the memory to create at least one text building unit according to the selected theory of discourse, analyzes the at least one text building unit according to the selected theory of discourse and displays the text building units;

wherein the selected theory of discourse analysis is selected from the list of at least Discourse Structures Theory, Linguistic Discourse Model, Rhetorical Structure Theory, Systemic Functional Grammar, and Tagmemics.

16. The system of claim 15, further comprising a reviewing circuit that reviews the analyzed text building units for consistency with the selected theory of discourse.

17. The system of claim 15, further comprising a structural representation building circuit to create a structural representation of the text building units according to the selected theory of discourse.

18. The system of claim 17, wherein the structural representation is a tree structure.

19. The system of claim 15, further comprising a concept highlighting circuit to highlight user designated important concepts.

20. The system of claim 15, further comprising a summary generating circuit that generates a summary based on the selected theory of discourse.

21. The system of claim 20, wherein the summary generating circuit identifies the root node and assigns it a rank;

recursively selects each remaining child node and for each child node that is a coordination node or a binary node, assigns each remaining child node the rank of the parent; and

for each child node that is a subordination node, assigns the rank of the parent to the subordinating node and the rank of the parent+1 to the subordinated node.

22. The system of claim 20, further comprising a concept comparator circuit.

23. The system of claim 22, wherein the concept comparator circuit provides a ratio of words from the user designated important concepts that are identified in the summary.

24. A method for teaching expository writing, comprising:

segmenting a text into at least one text building units based on the Linguistic Discourse Model theory of discourse;

analyzing each text building unit according to the Linguistic Discourse Model theory of discourse; and

providing, based on the analyzed at least one text building units, objective feedback for teaching expository writing.

25. A system for teaching expository writing, comprising:

an input device;

a display device;

a memory;

a segmenting circuit;

an analyzing circuit; and

a controller that segments a text received form the memory to create at least one text building unit according to the Linguistic Discourse Model theory of discourse, analyzes the at least one text building unit according to the Linguistic Discourse Model theory of discourse, displays the text building units, and provides, based on the analyzed at least one text building units, objective feedback for teaching expository writing.