System and method for dynamically determining the function of a lexical item based on context

• US 7,424,420 B2
• Filed: 02/11/2003
• Issued: 09/09/2008
• Est. Priority Date: 02/11/2003
• Status: Expired due to Fees

• Current Assignee: Fuji Xerox Company Limited (Xerox Holdings Corp.)
• Original Assignee: Fuji Xerox Company Limited (Xerox Holdings Corp.)
• Inventors: Polanyi, Livia, Zaenen, Annie
• Primary Examiner(s): Dorvil; Richemond
• Assistant Examiner(s): Saint Cyr; Leonard
• Application Number:
  US10/364,038
• Publication Number:
  US 20040158452A1
• Time in Patent Office: 2,037 Days
• Field of Search: None
• US Class Current: 704/8
• CPC Class Codes: G06F 40/253 Grammatical analysis; Style critique

Abstract

A method for adaptively determining the attitudinal function of a lexical item occurring in a natural language document, comprising determining a base valence of the lexical item; identifying a contextual valence shifter (CVS) wherein the lexical item is within scope of the CVS; and determining an actual valence of the lexical item by adjusting the base valence based on the CVS.

Claims

1. A method for adaptively determining the attitudinal function of a lexical item occurring in a natural language document, comprising:

determining a base valence of the lexical item;

identifying a contextual valence shifter (CVS) wherein the lexical item is within scope of the CVS;

determining an actual valence of the lexical item by adjusting the base valence based on the CVS; and

determining the attitudinal function of the lexical item, wherein the CVS has a negative impact on the base valence if the consequences of a not born-out expectation are negative and has a positive impact on the base valence if the consequences of the not born-out expectation are positive.

2. The method of claim 1 further comprising determining:

at least one additional CVS, where the additional CVS is different from the CVS identified in claim 1, where the additional CVS is one of;

a negator, an intensifier, a connector, and a modal.

3. The method of claim 2 wherein:

The additional intensifier CVS is a word or phrase used for emphasis or de-emphasis that strengthens or weaken the base valence, respectively.

4. The method of claim 2 wherein:

the additional connector CVS is a word or phrase that indicates a different point of view and neutralizes or negate the base valence.

5. The method of claim 2 wherein:

the additional modal CVS is a word or phrase that establishes a condition wherein the condition neutralizes or negate the base valence.

6. The method of claim 1 wherein:

the base valence represents positive or negative attitudinal information encoded in the lexical item.

7. The method of claim 1 wherein:

determining the base valence is based on taking into account the domain in which the lexical item occurs.

8. The method of claim 1 wherein:

determining the actual valence of the lexical item by adjusting the base valence based on a plurality of contextual valence shifters.

9. The method of claim 1 wherein:

the lexical item can be a CVS.

10. The method of claim 1 wherein:

the actual valence denotes an attitude of an author towards an entity or an event.

11. A method for adaptively determining the attitudinal function of a lexical item occurring in a natural language document, comprising:

categorizing the lexical item as positive, negative or neutral to determine a base valence of the lexical item;

analyzing the lexical item in context of a contextual valence shifter (CVS) to determine an actual valence of the lexical item;

wherein the CVS has a negative impact on the base valence if the consequences of a not born-out expectation are negative and has a positive impact on the base valence if the consequences of the not born-out expectation are positive; and

wherein the lexical item can be a CVS; and

wherein the actual valence denotes an attitude of an author towards an entity or an event.

12. The method of claim 11 further comprising determining:

at least one additional CVS, where the additional CVS is different from the CVS of claim 11, where the additional CVS is one of;

a negator, an intensifier, a connector, and a modal.

13. The method of claim 12 wherein:

the additional negator CVS is a word or phrase that can negate the base valence.

14. The method of claim 12 wherein:

The additional intensifier CVS is a word or phrase used for emphasis or de-emphasis that strengthens or weaken the base valence, respectively.

15. The method of claim 12 wherein:

the additional connector CVS is a word or phrase that indicates a different point of view and neutralizes or negate the base valence.

16. The method of claim 12 wherein:

the additional modal CVS is a word or phrase that establishes a condition wherein the condition neutralizes or negate the base valence.

17. The method of claim 11 wherein:

the base valence represents positive or negative attitudinal information encoded in the lexical item.

18. The method of claim 11 wherein:

determining the base valence is based on taking into account the domain in which the lexical item occurs.

19. The method of claim 11 wherein:

determining the actual valence of the lexical item by adjusting the base valence based on a plurality of contextual valence shifters.

20. A system for adaptively determining the attitudinal function of a lexical item occurring in a natural language document, comprising:

a base valence calculator to determine a base valence of the lexical item;

a contextual valence adjuster coupled to the base valence calculator, the contextual valence adjuster to determine an actual valence by adjusting the base valence based on a contextual valence shifter (CVS); and

an information extraction routine to determine the attitudinal function of the lexical item based on the actual valence, wherein the CVS is a presupposition;

wherein the CVS has a negative impact on the base valence if the consequences of a not born-out expectation are negative and has a positive impact on the base valence if the consequences of the not born-out expectation are positive.

21. The system of claim 20 wherein:

the base valence calculator utilizes a thesaurus; and

wherein the thesaurus provides the base valence of the lexical item.

22. The system of claim 21 wherein:

the thesaurus uses domain information to determine the base valence.

23. The system of claim 20 wherein:

the base valence calculator analyzes the natural language document to determine a domain for the lexical item.

24. The system of claim 20 further comprising determining:

at least one additional CVS, where the additional CVS is not a presupposition, where the additional CVS is one of;

a negator, an intensifier, a connector, and a modal.

25. The system of claim 24 wherein:

The additional intensifier CVS is a word or phrase used for emphasis or de-emphasis that strengthens or weaken the base valence, respectively.

26. The system of claim 24 wherein:

the additional connector CVS is a word or phrase that indicates a different point of view and neutralizes or negate the base valence.

27. The system of claim 24 wherein:

the additional modal CVS is a word or phrase that establishes a condition wherein the condition neutralizes or negate the base valence.

28. The system of claim 20 wherein:

the base valence represents positive or negative attitudinal information encoded in the lexical item.

29. The system of claim 20 wherein:

determining the actual valence of the lexical item by adjusting the base valence based on a plurality of contextual valence shifters.

30. The system of claim 20 wherein:

the lexical item can be a CVS.

31. The system of claim 20 wherein:

the actual valence denotes an attitude of an author towards an entity or an event.

32. A machine readable medium having instructions stored thereon that when executed by a processor cause a system to:

determine a base valence of the lexical item;

identify a contextual valence shifter (CVS) wherein the lexical item is within scope of the CVS;

determine an actual valence of the lexical item by adjusting the base valence based on the CVS; and

extract information to determine the attitudinal function of the lexical item based on the actual valence, wherein the CVS is a presupposition which has a negative impact on the base valence if the consequences of a not born-out expectation are negative and has a positive impact on the base valence if the consequences of the not born-out expectation are positive.

33. The machine readable medium of claim 32 further comprising determining:

at least one additional CVS, where the additional CVS is not a presupposition CVS, where the additional CVS is one of;

a negator, an intensifier, a connector, and a modal.

34. The machine readable medium of claim 33 wherein:

The additional intensifier CVS is a word or phrase used to emphasis or de-emphasis that strengthens or weaken the base valence, respectively.

35. The machine readable medium of claim 33 wherein:

the additional connector CVS is a word or phrase that indicates a different point of view and neutralizes or negate the base valence.

36. The machine readable medium of claim 33 wherein:

The additional modal CVS is a word or phrase that establishes a condition wherein the condition neutralizes or negate the base valence.

37. The machine readable medium of claim 32 wherein:

the base valence represents positive or negative attitudinal information encoded in the lexical item.

38. The machine readable medium of claim 32 wherein:

determining the base valence is based on taking into account the domain in which the lexical item occurs.

39. The machine readable medium of claim 32 wherein:

determining the actual valence of the lexical item by adjusting the base valence based on a plurality of contextual valence shifters.

40. The machine readable medium of claim 32 wherein:

the lexical item can be a CVS.

41. The machine readable medium of claim 32 wherein:

the actual valence denotes an attitude of an author towards an entity or an event.