View
123
Download
0
Embed Size (px)
DESCRIPTION
Citation preview
Generation of Descriptive Elements for Text
Mutsugu Kuboki, Kazuhide Yamamoto
Nagaoka University of Technology, Japan
1
2
What description about query is these texts?
Query is “LPF”
We can‟t recognize it immediately. It may be that the text may not describe query.
We want to know content at web search
results. ….But it is difficult.
3
We try to generate Descriptive Elements(DE).
Query is “LPF”
Structure,
Type, …
Background,
Work, …
…
Main works
1. Extraction Candidates of DEs
2. Assigning DEs to text (This work is tried by Japanese texts only)
4
Main works
1. Extraction Candidates of DEs
2. Assigning DEs to text (This work is tried by Japanese texts only)
5
Extraction of DEs
DEs are different of query.
Examples Apple: Kind, Size, Area-of-Production, … LPF: Role, Structure, Performance , …
We try to get candidates in advance.
6
Extraction of DEs
Extract DEs from web search results. We use following rules.
7
(1)Pattern
ex)
enforcement of
LawProtectingPersonalInformation(eng)
kojinjyouhouhogohou-no-shikou(jpn)
(2)DEs are one word in Japanese.
„noun or compound nouns‟ of „query‟
„query “no” nouns or compound nouns‟(jpn)
Note. Japanese word “no” means “of”
Candidates extraction Query
„law protecting personal information‟ (”kojinjouhouhogohou” in Japanese)
Data top 10,000 Google search results
Evaluation We evaluate candidate manually.
8
Result of candidates extraction
Candidates 366 Adequate DEs 289(79%) Inadequate DEs 77(21%)
Adequate)infraction, operation, influence, …
Inadequate)learning, expert, …
79% of candidates are useful.
9
Result of candidates extraction
Candidates 366 Adequate DEs 289(79%) Inadequate DEs 77(21%)
Next experiment use 54 DEs from adequate
Candidates.
10
Above results include a lot of low frequency
DEs. These DEs are rejected from candidates.
Main works
1. Extraction Candidates of DEs
2. Assigning DEs to text (This work is tried by Japanese texts only)
11
Method We assume that texts of same DE include same words.
12
Paragraph 1 ={w1,w2,w3,…} Paragraph 2 ={w2,w3,w4,…} …
Paragraphs DE: X
{w2,w3}
Trigger of DE X
Triggers construct 1, 2 and 3 morphemes.
(2)Extract
cooccurrence
words.
(1)Extract text
from the web.
(3)Collect Triggers.
Method We assume that same DE texts include same words.
13
{w2, w3}, {w4, w7,w9}, {w11},…
Triggers of DE X
Does text include Triggers?
YES
DE: X
No
This text is not DE X.
How to make Triggers(1)
14
1. Extract paragraphs which include
“query-no-DE(jpn)” from the web.
2. Extract the content words from the
paragraphs.
3. Extract cooccurrence words from the
same DE paragraphs.
Triggers
How to make Triggers(2)
If Triggers apply to following rules, these
are excluded from Triggers.
Appearance frequency is 10% or under of
whole paragraphs which include „query-no-
DE‟
Same to query words
15
How to make Triggers(3)
Try to pilot test.
And we use combination of following rules.
(1)[used Trigger] used by the pilot test
Effect to increase accuracy
(2)[unused Trigger] assign mistake over two
(3)[unused Trigger] used by over 2 Des
Lead to error (not decisive factor)
16
Result of cooccurrence Trigger
• 1, 2, 3 triggers are number of morphemes.
• (1)(2)(3) are restriction rules.
Type Recall Precision F value average
nominations
Data (100 texts) 0.72 0.06 0.10 54.0 1 Trigger (1) 0.70 0.07 0.13 41.4 2 Trigger (1) 0.70 0.08 0.14 36.5 3 Trigger (1) 0.62 0.09 0.16 27.3 1 Trigger (1)(2) 0.42 0.15 0.22 5.9 2 Trigger (1)(2) 0.54 0.10 0.17 20.9 3 Trigger (1)(2) 0.55 0.10 0.16 21.8 1 Trigger (1)(2)(3) 0.37 0.16 0.22 3.4 2 Trigger (1)(2)(3) 0.52 0.10 0.17 18.5 3 Trigger (1)(2)(3) 0.55 0.10 0.17 20.3
17
Result of cooccurrence Trigger
• High recall values and low precision values
• Restriction rule is effective (nomination is
decreasing)
Type Recall Precision F value average
nominations
Data (100 texts) 0.72 0.06 0.10 54.0 1 Trigger (1) 0.70 0.07 0.13 41.4 2 Trigger (1) 0.70 0.08 0.14 36.5 3 Trigger (1) 0.62 0.09 0.16 27.3 1 Trigger (1)(2) 0.42 0.15 0.22 5.9 2 Trigger (1)(2) 0.54 0.10 0.17 20.9 3 Trigger (1)(2) 0.55 0.10 0.16 21.8 1 Trigger (1)(2)(3) 0.37 0.16 0.22 3.4 2 Trigger (1)(2)(3) 0.52 0.10 0.17 18.5 3 Trigger (1)(2)(3) 0.55 0.10 0.17 20.3
18
Issues of proposed method
Low Precision Value.
We want to know factor to decide
DEs.
Let‟s try to use more strong rules.
Modification relation Triggers
Notice.
Next experiment uses 19 DEs for simplicity (Similar DEs are rejected from candidates)
19
Modification relation Triggers
Used patterns 1. noun and DEs
2. noun and synonym of DEs
3. noun and hyponym of DEs
Synonyms and hyponyms are obtained from
Japanese WordNet.
20
Result of modification relation Triggers
p/p=system out right answers
p/n=system out mistake answers
n/p=system doesn‟t looking for DE (answers have DE)
n/n=system does recognize non DE text 21
Trigger Prec. system/answer
p/p p/n n/p n/n All 0.31 11 24 181 1615 DE 0.67 6 3 - - Synonym 0.21 3 11 - - Hyponym 0.17 2 10 - - Answer
data - 192 - - 1708
Result of modification relation Triggers
22
Trigger Prec. system/answer
p/p p/n n/p n/n All 0.31 11 24 181 1615 DE 0.67 6 3 - - Synonym 0.21 3 11 - - Hyponym 0.17 2 10 - - Answer
data - 192 - - 1708
Results have a lot of mistakes.
Trigger is not effect to evaluate true or false?
check results
Result p/n(assigning errors)(1)
Almost Triggers are constructed by
words to relate DE.
23
22/24 results are constructed by
relation words.
Examples Operation(cabinet, citizen, month)
Enforcement-status(announcement,
cabinet, year)
Words of Triggers relate to DE.
But precision value is low.
Result p/n(assigning errors)(2)
Conclusion
Error factor isn‟t necessarily Trigger
words.
24
Only judgment that text have keywords
or not doesn‟t assure precision.
What factor does increase
precision?
Result p/n(system can‟t find DE)
how to decide DEs by people.
we check n/p(181 pairs) manually
25
Factor is unclear • 28 pairs(15%)
• 11 pair DE is
“description”
• Others are low
frequently.
Factor is clear • 153 pairs(85%)
• These have specific
expression. Word, Words or
Phrase
How to decide DEs by people
Conclusion
We use only part of text to decide
almost DE.(Text only explain query)
Point
don‟t use all text.
Example …Law protecting personal information
is established for fiscal year 2003…
26
Conclusions
Effect of Trigger
Trigger don‟t assure precision.
How to increase precision
Don‟t use all text.
System have to use only part of
text that explain query.
27
Future work
Assigning DEs use part of text
Look into…
• Effect of using part of text
• Other factor to decide DEs
28
29
Mistake in my paper…
I‟m sorry … III. Experiments and Results C. Assigning DE Using Restricted Triggers Please change (1) to (2).
30
Example of p/p
●Difinition(生存-living, 識別-recognize) 死者に関する情報であってもその内容が遺族等の生存する個人を識別できる場合には個人情報保護法の個人情報として取り扱う必要があります。
31
Example of p/n
● Effect(多い-many, 施行-enforcement) 主催した道中小企業家同友会帯広支部の石戸谷和政事務局長は「個人情報保護法といっても、正直、何から始めればいいのか分からない経営者が多い。施行が目の前に迫り、せっぱ詰まっている」と経営者たちの胸の内を代弁する。
32
Example of n/p
●影響(Effect) 情報漏洩罪が出てきた背景には、従業員が個人情報を漏洩するケースが多く、かつ技術による防御には限界があるという認識がある。情報セキュリティに完璧はありえない。完璧を求めなくとも情報セキュリティ対策にはコストがかかり、個人情報保護法の施行以来、企業は多大なコスト負担に泣いているという現状がある。
33