2017 Fiscal Year Annual Research Report
Framework for Studying Language Evolution using Large Scale Data
| Project/Area Number |
15K12158
|
|---|
| Research Institution | Kyoto University |
|---|
Principal Investigator |
Adam Jatowt 京都大学, 情報学研究科, 特定准教授 (00415861)
|
|---|
| Project Period (FY) |
2015-04-01 – 2018-03-31
|
| Keywords | word semantic change / document age / historical linguistics / term similarity |
|---|
| Outline of Annual Research Achievements |
In the last year we have completed implementing online system for word semantic evolution analysis based on Google Books ngram data.
We have also proposed an efficient method for across-time similarity estimation of terms based on dual hierarchical clustering structures. This work has been published at CIKM 2017 conference. At the same conference we have also published a demo paper proposing online system for automatic age estimation of any text.
Overall, the project resulted in a set of effective methods to find similar terms in different time periods as well as explain the similarity of detected terms, online visualization system for word evolution study as well as system for document age estimation and across-time comparison of large document collections.
|
