SYSTEM AND METHOD OF USING POS TAGGING FOR SYMBOL ASSIGNMENT

• US 20110161067A1
• Filed: 12/29/2009
• Published: 06/30/2011
• Est. Priority Date: 12/29/2009
• Status: Abandoned Application

• Current Assignee: Tobii Dynavox LLC (Tobii Technology AB)
• Original Assignee: Tobii Dynavox LLC (Tobii Technology AB)
• Inventors: CUNNINGHAM, BOB, LESHER, GREG
• Application Number:
  US12/648,683
• Publication Number:
  US 20110161067A1
• Time in Patent Office: Days
• US Class Current: 704/1
• CPC Class Codes: G06F 40/169 Annotation, e.g. comment data or footnotes
• CPC Class Codes: G06F 40/211 Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
• CPC Class Codes: G06F 40/268 Morphological analysis
• CPC Class Codes: G06F 40/30 Semantic analysis

Abstract

Systems and methods for automatically discovering and assigning symbols for identified text in a software application include identifying text for which symbol assignment is desired. The words within the identified text and selected surrounding words defining an observation sequence are subjected to a part of speech tagging algorithm to electronically determine one or more most likely part of speech tags for the identified text. Context relations between the identified text and selected surrounding keywords may also be identified. The identified text, part of speech tag(s) and/or determined relations are then analyzed to map the identified text to one or more identified word senses. Related word senses may also be analyzed to determine if any related word senses have symbols. One of the determined symbols may then be associated with the identified text such that the symbol is thereafter displayed in conjunction with or instead of the text in the application.

Claims

1. A method of automatically discovering and assigning symbols for identified text in a software application, comprising:

receiving electronic signals indicating identified text for which symbol assignment is desired;

electronically determining one or more most likely part of speech tags for the identified text;

electronically analyzing the identified text and the one or more most likely part of speech tags for the identified text to automatically establish a mapping of the identified text to one or more identified word senses;

electronically determining whether any of the identified word senses has an associated symbol; and

displaying one or more of the electronically determined associated symbols on an electronic display device.

2. The method of claim 1, wherein the part of speech tags from said first electronically determining step are selected from a tagset indicating basic parts of speech as well as syntactic or morpho-syntactic distinctions.

3. The method of claim 1, wherein the part of speech tags from said first electronically determining step are selected from a part of speech tagset containing between 20 and 100 possible tags.

4. The method of claim 1, wherein said step of electronically determining one or more most likely part of speech tags for the identified text comprises:

extracting an observation sequence of text including the identified text and surrounding words; and

assigning the most likely part of speech tag for each word in the observation sequence.

5. The method of claim 4, wherein said assigning step comprises employing one or more of a first-order Viterbi algorithm, a second-order Viterbi algorithm and a forward-backward algorithm to assign part of speech tags.

6. The method of claim 1, wherein said step of electronically determining one or more most likely part of speech tags for the identified text comprises:

extracting an observation sequence of text including the identified text and surrounding words; and

generating a list of possible tags and corresponding probabilities of occurrence for the one or more words in the identified text.

7. The method of claim 1, further comprising:

electronically selecting one or more related word senses that are related to the one or more identified word senses; and

electronically determining whether the one or more selected related word senses has an associated symbol.

8. The method of claim 7, further comprising providing a graphical user interface to a user for manual selection of a symbol to associate with the identified text when said electronically determining steps results in a determination that neither the identified word senses nor the selected related word senses have associated symbols.

9. The method of claim 7, further comprising a step of applying an automated modification to a symbol determined to be associated with a related word sense before displaying such symbol.

10. The method of claim 1, further comprising displaying multiple word senses on a graphical user interface for subsequent user selection when multiple word senses are mapped in said electronically analyzing step or when multiple associated symbols are identified in said second electronically determining step.

11. The method of claim 1, wherein said displaying step more particularly comprises displaying the identified text in conjunction with the assigned selected symbol on an electronic display device.

12. The method of claim 1, further comprising a step of electronically determining relations among the identified text and selected surrounding keywords, and wherein said electronically analyzing step additionally considers any determined relations in mapping the identified text to one or more identified word senses.

13. An electronic device, comprising:

at least one electronic input device configured to receive electronic input from a user indicating identified text for which symbol assignment is desired;

at least one processing device;

at least one memory comprising computer-readable instructions for execution by said at least one processing device, wherein said processing device is configured to determine one or more most likely part of speech tags for the identified text, analyze the identified text and the one or more most likely part of speech tags for the identified text to automatically establish a mapping of the identified text to one or more identified word senses, and determine whether any of the identified word senses has an associated symbol; and

at least one electronic output device configured to display one or more of the electronically determined associated symbols as visual output.

14. The electronic device of claim 13, wherein said electronic device comprises a speech generation device that comprises at least one speaker for providing audio output.

15. The electronic device of claim 13, wherein said processing device is further configured as part of determining one or more most likely part of speech tags for the identified text to extract an observation sequence of text including the identified text and surrounding words, and assign the most likely part of speech tag for each word in the observation sequence by employing one or more of a first-order Viterbi algorithm, a second-order Viterbi algorithm, and a forward-backward algorithm.

16. The electronic device of claim 13, wherein said processing device is further configured as part of determining one or more most likely part of speech tags for the identified text to extract an observation sequence of text including the identified text and surrounding words, and generate a list of possible tags and corresponding probabilities of occurrence for one or more words in the identified text.

17. The electronic device of claim 13, wherein said at least one output device is further configured to display multiple word senses for subsequent user selection when multiple word senses are mapped to the identified text or when multiple symbols are identified as being associated with the identified word senses or selected related word senses.

18. The electronic device of claim 13, wherein said at least one output device is configured to display the identified text in conjunction with an assigned selected symbol.

19. The electronic device of claim 13, wherein said at least one processing device is further configured to electronically determine relations among the identified text and selected surrounding keywords, and wherein the subsequent analysis additionally considers any determined relations in mapping the identified text to one or more identified word senses.

20. The electronic device of claim 13, wherein said at least one processing device is further configured to select one or more related word senses that are related to the one or more identified word senses, and determine whether the one or more selected related word senses has an associated symbol.

21. The electronic device of claim 20, wherein said at least one processing device is further configured to apply an automated modification to a symbol determined to be associated with a related word sense before displaying such symbol.

22. A computer readable medium comprising executable instructions configured to control a processing device to:

receive electronic signals from an input device indicating identified text for which symbol assignment is desired;

electronically determine one or more most likely part of speech tags for the identified text;

electronically analyze the identified text and the one or more most likely part of speech tags for the identified text to automatically establish a mapping of the identified text to one or more identified word senses;

electronically determine whether any of the identified word senses has an associated symbol; and

display one or more of the electronically determined associated symbols on an electronic display device.

23. The computer readable medium of claim 22, wherein said executable instructions are further configured to extract an observation sequence of text including the identified text and surrounding words, and assign the most likely part of speech tag for each word in the observation sequence using one or more of a first-order Viterbi algorithm, a second-order Viterbi algorithm and a forward-backward algorithm.

24. The computer readable medium of claim 22, wherein said executable instructions are further configured to extract a sequence of text including the identified text and surrounding words, and generate a list of possible tags and corresponding probabilities of occurrence for one or more words in the identified text.

25. The computer readable medium of claim 22, wherein said executable instructions are further configured to select one or more related word senses that are related to the one or more identified word senses, and determine whether the one or more selected related word senses has an associated symbol.

26. The computer readable medium of claim 25, wherein said executable instructions are further configured to apply an automated modification to a symbol determined to be associated with a related word sense before displaying such symbol.

27. The computer readable medium of claim 22, wherein said executable instructions are further configured to display multiple word senses on a graphical user interface for subsequent user selection when multiple word senses are mapped via the electronically analyzing step or when multiple associated symbols are identified in said second electronically determining step.