Apparatus and method for detecting named entity

1. A named-entity detection apparatus comprising:

a candidate-named-entity extraction module detecting a candidate-named-entity based on an initial learning example and feature information regarding morphemes constituting an inputted sentence, the candidate-named-entity extraction module providing a tagged sentence including the detected candidate-named-entity, wherein the candidate-named-entity extraction module is hardware module;

a storage module storing information regarding a named-entity dictionary and a rule; and

a learning-example-regeneration module determining whether the candidate-named-entity included in the provided sentence is a valid named-entity, based on the named-entity dictionary and the rule, and providing the sentence as a learning example, based on a determination result, so that a probability of named-entity candidate detection is gradually updated,

wherein the candidate-named-entity extraction module determines a class of each morpheme by using a learning model based on the feature information, and provides a tagged sentence by adding determined class information as a tag,

wherein the learning example provided by the learning-example-regeneration module is reflected in the learning module as a negative example when the rule is violated,

wherein the probability of detecting the named-entity of the candidate-named-entity extraction module is gradually updated in the learning module when the learning example is a negative example,

wherein the feature information comprises a word feature, a part-of-speech feature, a concept feature, an adjacent verb feature, and an adjacent verb concept feature, and

wherein the concept feature comprises ontological concept information of a current morpheme as well as three morphemes before and after the current morpheme.

2. The named-entity detection apparatus of claim 1 , wherein the learning model comprises a Bayesian learning model.

3. The named-entity detection apparatus of claim 1 , wherein the named-entity dictionary comprises unambiguous named-entities.

4. The named-entity detection apparatus of claim 1 , wherein the rule comprises an error inspection rule using a meaning string pattern.

5. The named-entity detection apparatus of claim 1 , wherein the rule comprises an error inspection rule using an excluded word list.

6. The named-entity detection apparatus of claim 1 , wherein the learning-example-regeneration module provides the sentence including the candidate-named-entity as a positive learning example when the candidate-named-entity is included in the named-entity dictionary.

7. A named-entity detection method comprising:

detecting a candidate-named-entity based on an initial learning example and feature information regarding morphemes constituting an inputted sentence and providing a tagged sentence including the detected candidate-named-entity by a candidate-named-entity extraction module, wherein the candidate-named entity extraction module is a hardware module;

finally determining whether the candidate-named-entity included in the provided sentence is a valid named-entity, based on pre-stored named-entity dictionary and rule by learning-example regeneration module, and

providing the sentence as a learning example, based on a determination result, so that a probability of candidate-named-entity detection is gradually updated by the learning-example-regeneration module,

wherein, in the detecting, a class of each morpheme is determined by using a learning model based on the feature information, and a tagged sentence is provided after adding determined class information as a tag,

wherein, in the providing, the learning example is reflected in the learning model as a negative example when the rule is violated,

wherein the probability of detecting the named-entity of the learning-example-regeneration module is gradually updated in the learning module when the learning example is a negative example,

wherein the feature information comprises a word feature, a part-of-speech feature, a concept feature, an adjacent verb feature, and an adjacent verb concept feature, and

wherein the concept feature comprises ontological concept information of a current morpheme as well as three morphemes before and after the current morpheme.

8. The named-entity detection method of claim 7 , wherein the learning model comprises a Bayesian learning model.

9. The named-entity detection method of claim 7 , wherein the named-entity dictionary comprises unambiguous named-entities.

10. The named-entity detection method of claim 7 , wherein the rule comprises an error inspection rule using a meaning string pattern.

11. The named-entity detection method of claim 7 , wherein the rule comprises an error inspection rule using an excluded word list.

12. The named-entity detection method of claim 7 , wherein, in the providing, the sentence including the candidate-named-entity is provided as a positive learning example when the candidate-named-entity is included in the named-entity dictionary.

13. A named-entity detection system comprising:

a voice-recognition unit converting an utterance into a recognized sentence;

a morpheme analysis unit analyzing morphemes of the recognized sentence; and

a named-entity detection unit detecting named-entities from the analyzed sentence, the named-entity detection unit comprising

a model-learning module learning a model for named-entity extraction from at least one example,

a named-entity candidate extraction module extracting all possible named-entity candidates based on feature information regarding morphemes constituting the recognized sentence and either a model learned by the model-learning module or an initial learning example, and providing a tagged sentence including all the extracted named-entity candidates,

a storage module storing a named-entity dictionary and a rule, and

a learning-example-regeneration module determining whether the at least one named-entity candidate included in the provided tagged sentence is a valid named-entity, based on the named-entity dictionary and the rule, and providing the tagged sentence as a learning example to the model-learning module, based on a determination result, so as to increase a probability of named-entity candidate detection,

wherein the named-entity candidate extraction module is a hardware module; and

wherein, the learning example is reflected in the model-learning module as a negative example when the rule is violated,

wherein the probability of detecting the named-entity of the named-entity detection unit is gradually updated in the learning module when the learning example is a negative example,

wherein the feature information comprises a word feature, a part-of-speech feature, a concept feature, an adjacent verb feature, and an adjacent verb concept feature, and

wherein the concept feature comprises ontological concept information of a current morpheme as well as three morphemes before and after the current morpheme.

14. The system of claim 13 , further comprising a sentence-input unit receiving an inputted sentence, wherein the morpheme analysis unit analyzes morphemes of the inputted sentence.

15. A named-entity detection method comprising:

extracting a candidate named-entity, which is a potential named-entity, from a user utterance including a sentence using an initial learning example and feature information regarding morphemes constituting the sentence by a candidate-named-entity extraction module, wherein the candidate-named-entity extraction module is a hardware module;

determining whether a candidate named-entity matches an item registered in a dictionary by a learning-example-regeneration module;

verifying the candidate named-entity as a named-entity when the candidate named-entity matches an item registered in the dictionary and providing the candidate named-entity as a new positive learning example to a learning model by the learning-example-regeneration module; and

determining whether the candidate named-entity violates a rule when the candidate named-entity does not match an item registered in the dictionary, providing the candidate named-entity as a new negative learning example to the learning model when the candidate violates a rule, updating the probability of detecting the named-entity of the learning-example-regeneration module gradually when the new negative learning example violates the rule, and verifying the candidate named-entity as a named-entity when the candidate named-entity does not violate any rule,

wherein the feature information comprises a word feature, a part-of-speech feature, a concept feature, an adjacent verb feature, and an adjacent verb concept feature, and

wherein the concept feature comprises ontological concept information of a current morpheme as well as three morphemes before and after the current morpheme.

16. The method of claim 15 , wherein the rule is an error inspection rule using at least one selected from the group consisting of a meaning string pattern and an excluded word list.

17. A non-transitory computer-readable storage medium encoded with processing instructions for causing a processor to execute the method of claim 7 .

18. A non-transitory computer-readable storage medium encoded with processing instructions for causing a processor to execute the method of claim 15 .