Presentation | 2012-08-30 Extraction of Sentences Describing Problems from Sales Force Management System Texts Daigo SUGIHARA, Tomoko OHKUMA, Koji SATAKE, Yasuhide MIURA, Keigo HATTORI, Hiroshi MASUICHI, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Sales persons are recommended to know customers' problems, because knowing customers' problems will lead to better proposals for customers. Knowing problems about services or products provided to their customers will lead to improvement of their services or products. Therefore we tried to extract sentences describing problems from texts in sales force management system, with aim of analyzing various problems or searching problems and solution in the past. Surveying texts in sales force management system, we found out that definition for sentences describing problems we should extract is "Sentences described as object or result for solution, such as troubled situation or desired goal". We defined extraction of sentences describing problems as classification whether input sentence is describing problems or not. Our experimental result showed that our SVM classifier achieved F-measure of 0.40 and the most effective features were those about vocaburaries such as negative expressions from polarity dictionaries and function words representing demand or capability. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | SVM / Binary Classificatin / Sentence Extraction / Sales Force Management System / Customers' Problems |
Paper # | NLC2012-11 |
Date of Issue |
Conference Information | |
Committee | NLC |
---|---|
Conference Date | 2012/8/23(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Natural Language Understanding and Models of Communication (NLC) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Extraction of Sentences Describing Problems from Sales Force Management System Texts |
Sub Title (in English) | |
Keyword(1) | SVM |
Keyword(2) | Binary Classificatin |
Keyword(3) | Sentence Extraction |
Keyword(4) | Sales Force Management System |
Keyword(5) | Customers' Problems |
1st Author's Name | Daigo SUGIHARA |
1st Author's Affiliation | () |
2nd Author's Name | Tomoko OHKUMA |
2nd Author's Affiliation | / Communication Technology Laboratory. Reserch & Technology Group. Fuji Xerox Co., Ltd. |
3rd Author's Name | Koji SATAKE |
3rd Author's Affiliation | Communication Technology Laboratory. Reserch & Technology Group. Fuji Xerox Co., Ltd. |
4th Author's Name | Yasuhide MIURA |
4th Author's Affiliation | Communication Technology Laboratory. Reserch & Technology Group. Fuji Xerox Co., Ltd. |
5th Author's Name | Keigo HATTORI |
5th Author's Affiliation | Communication Technology Laboratory. Reserch & Technology Group. Fuji Xerox Co., Ltd. |
6th Author's Name | Hiroshi MASUICHI |
6th Author's Affiliation | |
Date | 2012-08-30 |
Paper # | NLC2012-11 |
Volume (vol) | vol.112 |
Number (no) | 196 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |