JP2018116512A5 - Key sentence extraction method or key sentence extraction device - Google Patents
Key sentence extraction method or key sentence extraction device Download PDFInfo
- Publication number
- JP2018116512A5 JP2018116512A5 JP2017007134A JP2017007134A JP2018116512A5 JP 2018116512 A5 JP2018116512 A5 JP 2018116512A5 JP 2017007134 A JP2017007134 A JP 2017007134A JP 2017007134 A JP2017007134 A JP 2017007134A JP 2018116512 A5 JP2018116512 A5 JP 2018116512A5
- Authority
- JP
- Japan
- Prior art keywords
- sentence
- word
- key
- keyword
- detecting
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000605 extraction Methods 0.000 title claims 10
- 238000001514 detection method Methods 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims 4
- 239000000284 extract Substances 0.000 claims 4
- 230000000875 corresponding Effects 0.000 claims 2
Description
上記課題を解決するために、本発明は、センテンスの集まりである文章からキーセンテンスを抽出するキーセンテンス抽出方法であって、予めキーワードを記憶するキーワード記憶ステップと、予め除外ワードを記憶する除外ワード記憶ステップと、所定のセンテンスから前記キーワードを検出するキーワード検出ステップと、所定のセンテンスから前記除外ワードを検出する除外ワード検出ステップと、を有し、前記文章に新たにセンテンスが追加されたならば、追加されたセンテンスに前記キーワードを検出し、除外ワードを検出しなかったならば、前記追加されたセンテンスをキーセンテンスとして抽出することを特徴とする。
または、上記課題を解決するために、センテンスの集まりである文章からキーセンテンスを抽出するキーセンテンス抽出装置であって、予めキーワードを記憶するキーワード記憶手段と、予め除外ワードを記憶する除外ワード記憶手段と、所定のセンテンスから前記キーワードを検出するキーワード検出手段と、所定のセンテンスから前記除外ワードを検出する除外ワード検出手段と、を有し、前記文章に新たにセンテンスが追加されたならば、追加されたセンテンスに前記キーワードを検出し、除外ワードを検出しなかったならば、前記追加されたセンテンスをキーセンテンスとして抽出することを特徴とする。
In order to solve the above problems, the present invention provides a key sentence extracting method for extracting a key sentence from a sentence which is a collection of sentences, a keyword storing step for storing a keyword in advance, and an excluded word for storing an excluded word in advance. A storage step, a keyword detection step for detecting the keyword from a predetermined sentence, and an excluded word detection step for detecting the exclusion word from a predetermined sentence, and if a sentence is newly added to the sentence If the keyword is detected in the added sentence and no exclusion word is detected, the added sentence is extracted as a key sentence.
Alternatively, in order to solve the above problem, a key sentence extracting device for extracting a key sentence from a sentence that is a collection of sentences, a keyword storage unit that stores keywords in advance and an excluded word storage unit that stores exclusion words in advance. And a keyword detecting means for detecting the keyword from a predetermined sentence, and an excluded word detecting means for detecting the excluded word from the predetermined sentence. If a sentence is newly added to the sentence, an addition is made. If the keyword is detected in the added sentence and no excluded word is detected, the added sentence is extracted as a key sentence.
Claims (5)
予めキーワードを記憶するキーワード記憶ステップと、 A keyword storage step for storing keywords in advance;
予め除外ワードを記憶する除外ワード記憶ステップと、 An excluded word storage step for storing the excluded word in advance;
所定のセンテンスから前記キーワードを検出するキーワード検出ステップと、 A keyword detection step of detecting the keyword from a predetermined sentence;
所定のセンテンスから前記除外ワードを検出する除外ワード検出ステップと、を有し、 An excluded word detecting step of detecting the excluded word from a predetermined sentence,
前記文章に新たにセンテンスが追加されたならば、追加されたセンテンスに前記キーワードを検出し、除外ワードを検出しなかったならば、前記新たに追加されたセンテンスをキーセンテンスとして抽出することを特徴とするキーセンテンス抽出方法。 If a sentence is newly added to the sentence, the keyword is detected in the added sentence, and if no exclusion word is detected, the newly added sentence is extracted as a key sentence. Key sentence extraction method.
意見の同意を示すワードを記憶する同意ワード記憶ステップと、 A consent word storage step for storing a word indicating consent of opinion;
前記文章に第一のセンテンスが追加され、追加されたセンテンスに前記キーワードおよびまたは除外ワードを検出すると、第二のセンテンスが追加されたことを抽出する第二センテンス抽出手段と、 A second sentence extracting means for extracting the second sentence when the first sentence is added to the sentence and the keyword and / or the excluded word are detected in the added sentence;
前記第二センテンス検出手段が、第二のセンテンスが追加されたことを抽出すると、当該第二のセンテンスに同意ワードを検出する同意ワード検出手段と、When the second sentence detection means extracts that the second sentence has been added, an agreement word detection means for detecting an agreement word in the second sentence;
前記同意ワード検出手段が、前記第二のセンテンスに同意ワードを検出すると、前記第一のセンテンスおよび第二のセンテンスをキーセンテンスとして抽出することを特徴とするキーセンテンス抽出方法。 A key sentence extracting method, wherein when the consent word detecting means detects an agreement word in the second sentence, the first sentence and the second sentence are extracted as key sentences.
予め前記除外ワードに対応づけて平常文を表す文末表現を登録するセンテンス変換テーブル記憶ステップと、
前記第二センテンス検出手段が第二のセンテンスを抽出し、当該第二のセンテンスに同意ワードが含まれていることを検出したならば、前記第一のセンテンスに含まられる除外ワードを対応する平常文の文章表現に変換する平常文変換ステップと、をさらに有し、
前記平常文変換ステップによって変換された変換センテンスをキーセンテンスとして抽出することを特徴とするキーセンテンス抽出方法。 In the key sentence extraction method according to claim 2,
A sentence conversion table storage step for registering a sentence end expression representing a normal sentence in association with the exclusion word in advance;
If the second sentence detection means extracts the second sentence and detects that the second sentence includes a consent word, the ordinary sentence corresponding to the exclusion word included in the first sentence is detected. A normal sentence conversion step for converting the sentence expression into
A key sentence extracting method, wherein a conversion sentence converted by the normal sentence conversion step is extracted as a key sentence.
前記キーワード記憶ステップは、キーワード毎に分類情報が対応付けられており、
前記キーワード検出ステップは、キーワードを二つ以上検出した場合、当該キーワードに対応する分類情報を参照し、参照した情報が二種類以上存在する場合に、抽出したセンテンスをキーセンテンスとして抽出することを特徴とするキーセンテンス抽出方法。 The key sentence extraction method according to claim 1,
In the keyword storing step, classification information is associated with each keyword,
The keyword detection step refers to classification information corresponding to the keyword when two or more keywords are detected, and extracts the extracted sentence as a key sentence when there are two or more types of referenced information. Key sentence extraction method.
予めキーワードを記憶するキーワード記憶手段と、 Keyword storage means for storing keywords in advance;
予め除外ワードを記憶する除外ワード記憶手段と、 An excluded word storage means for storing the excluded word in advance;
所定のセンテンスから前記キーワードを検出するキーワード検出手段と、 Keyword detecting means for detecting the keyword from a predetermined sentence;
所定のセンテンスから前記除外ワードを検出する除外ワード検出手段と、を有し、 An excluded word detecting means for detecting the excluded word from a predetermined sentence,
前記文章に新たにセンテンスが追加されたならば、追加されたセンテンスに前記キーワードを検出し、除外ワードを検出しなかったならば、前記追加されたセンテンスをキーセンテンスとして抽出することを特徴とするキーセンテンス抽出装置。 If a sentence is newly added to the sentence, the keyword is detected in the added sentence, and if no exclusion word is detected, the added sentence is extracted as a key sentence. Key sentence extraction device.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2017007134A JP2018116512A (en) | 2017-01-19 | 2017-01-19 | Important item extracting method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2017007134A JP2018116512A (en) | 2017-01-19 | 2017-01-19 | Important item extracting method |
Publications (2)
Publication Number | Publication Date |
---|---|
JP2018116512A JP2018116512A (en) | 2018-07-26 |
JP2018116512A5 true JP2018116512A5 (en) | 2019-09-12 |
Family
ID=62985136
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
JP2017007134A Pending JP2018116512A (en) | 2017-01-19 | 2017-01-19 | Important item extracting method |
Country Status (1)
Country | Link |
---|---|
JP (1) | JP2018116512A (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR102155854B1 (en) * | 2019-12-09 | 2020-09-15 | 주식회사 크라우드웍스 | Keyword management method and apparatus for collecting various sentences |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH11272686A (en) * | 1998-03-19 | 1999-10-08 | Nippon Telegr & Teleph Corp <Ntt> | Method and device for important document sentence extraction and record medium where important document sentence extracting program is recorded |
JP2004177777A (en) * | 2002-11-28 | 2004-06-24 | Minolta Co Ltd | Minute preparation system |
US9092746B2 (en) * | 2009-06-29 | 2015-07-28 | Masaaki Tokuyama | Workflow processing program, information processing device and workflow processing method |
JP2016102920A (en) * | 2014-11-28 | 2016-06-02 | 京セラドキュメントソリューションズ株式会社 | Document record system and document record program |
JP2016144024A (en) * | 2015-02-02 | 2016-08-08 | 株式会社ナカヨ | Telephone apparatus with voice memo storage function |
-
2017
- 2017-01-19 JP JP2017007134A patent/JP2018116512A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP2016508264A5 (en) | ||
RU2014112242A (en) | METHOD OF ANALYSIS OF TONALITY OF TEXT DATA | |
GB2541581A (en) | Retrieving multi-generational stored data in a dispersed storage network | |
WO2015061046A3 (en) | Method and apparatus for performing topic-relevance highlighting of electronic text | |
WO2014022790A3 (en) | Method for using pauses detected in speech input to assist in interpreting the input during conversational interaction for information retrieval | |
GB201019808D0 (en) | Incremental browser-based device fingerprinting | |
WO2014041549A3 (en) | Document mining with relation extraction | |
WO2011126755A3 (en) | Detecting position of word breaks in a textual line image | |
CL2014002859A1 (en) | Method and system for using negative examples of words in a speech recognition system, in which the method comprises defining a set of words, identifying a set of negative examples of said words, performing a keyword recognition in said sets, determining values of word trust in said sets, identify at least one candidate word from said set of words, compare trust values, accept the candidate word. | |
WO2014183956A3 (en) | Social media content analysis and output | |
JP2014149848A5 (en) | ||
WO2013146394A4 (en) | Information processing terminal and method, and information management apparatus and method | |
EP2372571A3 (en) | Related search system and method based on resource description framework network | |
CN104765882B (en) | A kind of internet site statistical method based on web page characteristics character string | |
Meng et al. | Measuring semantic similarity of word pairs using path and information content | |
CN105630822A (en) | Method for marking similar contents in patent retrieval in red color | |
Körtvélyessy | Evaluative morphology and language universals | |
JP2018116512A5 (en) | Key sentence extraction method or key sentence extraction device | |
CN102591976A (en) | Text characteristic extracting method and document copy detection system based on sentence level | |
RU2013113415A (en) | RECOMMENDER SYSTEM USING A COMPATIBLE PROFILE | |
JP2015028739A5 (en) | ||
JP2018077611A5 (en) | ||
CN105608079A (en) | World patent retrieval method | |
MY182881A (en) | A method and system for automated entity recognition | |
Nandini et al. | Dengue detection and prediction System using data mining with Frequency analysis |