DOCUMENT PROCESSING METHOD AND SYSTEM

• US 20100306248A1
• Filed: 05/25/2010
• Published: 12/02/2010
• Est. Priority Date: 05/27/2009
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Bao, Sheng Hua, Cui, Jie, Zhang, Li, Su, Zhong, Su, Hui
• Granted Patent: US 8,359,327 B2
• Time in Patent Office: Days
• US Class Current: 707/769
• CPC Class Codes: G06F 16/34 Browsing; Visualisation therefor
• CPC Class Codes: G06F 16/93 Document management systems

Abstract

A method and system for expanding a document set as a search data source in the field of business related search. The present invention provides a method of expanding a seed document in a seed document set. The method includes identifying one or more entity words of the seed document; identifying one or more topic words identifying one or more topic words related to the based entity word in the seed document where the entity word is located; forming an entity word-topic word pair from each identified topic word and the entity word on the basis of which each topic word is identified; and obtaining one or more expanded documents through web by taking the entity word and topic word in the each entity word-topic word pair as key words at the same time. A system for executing the above method is also provided.

Claims

1. A method for expanding a seed document in a seed document set, wherein the seed document set comprises at least one seed document, the method comprising:

identifying one or more entity words of the seed document, wherein the entity words are words indicating focused entities of the seed document;

identifying, based on each identified entity word, one or more topic words related to the based entity word in the seed document where the entity word is located;

forming an entity word-topic word pair from each identified topic word and the entity word as the basis for identifying the each identified topic word; and

obtaining one or more expanded documents through the web by taking the entity word and topic word in each entity word-topic word pair as key words at the same time, wherein the expanded documents comprise not only the entity word in the each entity word-topic word pair but also the topic word in the each entity word-topic word pair.

2. The method according to claim 1, wherein the step of identifying, based on each identified entity word, one or more topic words related to the based entity word in the seed document where the entity word is located further comprises:

identifying one or more topic words related to the based entity word in the seed document where the entity word is located, based on a distance between words other than the one or more entity words comprised in the seed document and the based entity words.

3. The method according to claim 1, wherein the step of identifying, based on each identified entity word, one or more topic words related to the based entity word in the seed document where the entity word is located comprises:

identifying one or more topic words related to the based entity word in the seed document where the entity word is located, based on a frequency of other words than the one or more entity words comprised in the seed document and the based entity word appearing in a same sentence in the seed document.

4. The method according to claim 1, further comprising receiving a recommended seed document to form the seed document set.

5. The method according to claim 1, wherein one or more entity words of the seed document are identified with focused named entity recognition (FNER) technology.

6. The method according to claim 1, wherein one or more topic words of the seed document are identified with focused topic detection (FTD) technology.

7. A method for filtering a candidate document in a candidate document set, wherein the candidate document set comprises at least one candidate document, the method comprising:

receiving one or more entity word-topic word pairs;

identifying one or more entity words of the candidate document, wherein the entity words are words indicating focused entities of the candidate document;

identifying, based on each identified entity word, one or more topic words related to the based entity words in the candidate document where the entity word is located;

determining whether to add the candidate document into a filtered document set using the entity words and topic words in the given entity word-topic word pairs and the identified entity words and topic words in the candidate document; and

adding the candidate document into a filtered document set in response to determining that the candidate document should be added into said filtered document set, wherein;

each of the given entity word-topic word pairs comprise an entity word and a topic word;

all entity words in the entity word-topic word pair form an entity word set; and

all topic words in the entity word-topic word pair where each entity word is form a topic word set corresponding to the entity word.

8. The method according to claim 7, wherein identifying, based on each identified entity word, one or more topic words related to the based entity words in the candidate document where the entity word is located comprises:

identifying one or more topic words related to the based entity word in the candidate document where the entity word is located, based on a distance between words other than the one or more entity words comprised in the candidate document and the based entity words.

9. The method according to claim 7, wherein identifying, based on each identified entity word, one or more topic words related to the based entity words in the candidate document where the entity word is located, comprises:

identifying one or more topic words related to the based entity word in the seed document where the entity word is located, based on a frequency of other words than the one or more entity words comprised in the seed document and the based entity words appearing in a same sentence in the seed document.

10. The method according to claim 7, wherein the step of determining whether to add the candidate document into a filtered document set using the entity words and topic words in the given entity word-topic word pairs and the identified entity words and topic words in the candidate document further comprises:

determining not to add the candidate document into the filtered document set in response to a determination that the entity words in the candidate document are different from any entity word in the entity word set.

11. The method according to claim 7, wherein determining whether to add the candidate document into a filtered document set using the entity words and topic words in the given entity word-topic word pairs and the identified entity words and topic words in the candidate document further comprises:

determining to not add the candidate document into the filtered document set, in response to a determination that an entity word of the candidate document is identical to a certain entity word in the entity word set while a topic word identified in the candidate document based on an entity word in the candidate document is different from any topic word in the topic word set corresponding to a certain entity word in the entity word set.

12. The method according to claim 7, wherein the step of determining whether to add the candidate document into a filtered document set using the entity words and topic words in the given entity word-topic word pairs and the identified entity words and topic words in the candidate document further comprises:

determining to add the candidate document into the filtered document set, in response to a determination that an entity word of the candidate document is identical to a certain entity word in the entity word set of the given entity word-topic word pairs while a topic word identified in the candidate document based on an entity word in the candidate document is identical to a certain topic word in the topic word set corresponding to a certain entity word in the entity word set.

13. The method according to claim 7, wherein one or more entity words of the candidate document are identified with focused named entity recognition (FNER) technology.

14. The method according to claim 7, wherein one or more topic words of the candidate document are identified with focused topic detection (FTD) technology.

15. The method according to claim 7, wherein the candidate document set comprises an expanded document wherein an expanded document comprises not only an entity word in an entity word-topic word pair but also a topic word in the entity word-topic word pair.

16. The method according to claim 7, wherein the given entity word-topic word pairs are entity word-topic word pairs identified in all seed documents in a seed document set.

17. A system for expanding a seed document in a seed document set, wherein the seed document set comprises at least one seed document, the system comprising:

entity word identifying means for identifying one or more entity words of the seed document, the entity words being words indicating focused entities of the seed document;

topic word identifying means for identifying, based on each identified entity word, one or more topic words related to the based entity word in the seed document where the entity word is located;

pairing means for forming an entity word-topic word pair from each identified topic word and the entity word based on which the each topic word is identified; and

document expanding means for obtaining one or more expanded documents through the web by taking the entity word and topic word in the each entity word-topic word pair as key words at the same time, the expanded documents comprising not only the entity word in each entity word-topic word pair but also the topic word in the each entity word-topic word pair.

18. A system according to claim 17, wherein the topic word identifying means is configured to identify one or more topic words of the seed document with focused topic detection technology (FTD).

19. A system for filtering a candidate document in a candidate document set, wherein the candidate document set comprises at least one candidate document, the system comprising:

receiving means for receiving one or more entity word-topic word pairs;

entity word identifying means for identifying one or more entity words of the candidate document, the entity words being words indicating focused entities of the document;

topic word identifying means for identifying, based on the identified each entity word, one or more topic words related to the based entity word in the candidate document where the entity word is located; and

determining means for determining whether to add the candidate document into a filtered document set using the entity words and topic words in the given entity word-topic word pairs and the identified entity words and topic words in the candidate document and for adding the candidate document into a filtered document set in response to a determining result yes, wherein;

each of the given entity word-topic word pairs comprise an entity word and a topic word;

all entities in the entity word-topic word pair form an entity word set; and

all topic words in the entity word-topic word pair where each entity word is located forming a topic word set corresponding to the entity word.