2022 Fiscal Year Research-status Report
Linking Vision and Language through Computational Modelling
| Project/Area Number |
19K12733
|
|---|
| Research Institution | Kobe City University of Foreign Studies |
|---|
Principal Investigator |
CHANG Franklin 神戸市外国語大学, 外国語学部, 教授 (60827343)
|
|---|
| Project Period (FY) |
2019-04-01 – 2024-03-31
|
| Keywords | Vision / Language / Learning / Event understanding / Computational model / Deep Learning / Priming / Verbs |
|---|
| Outline of Annual Research Achievements |
I have written a paper on a deep learning model of how visual input is used to select verbs. The model is trained on data from human experiments on adults and the model was tested by comparing its verb use to children and adults. This paper has been accepted at Cognitive Science.
|
| Current Status of Research Progress |
Current Status of Research Progress
2: Research has progressed on the whole more than it was originally planned.
Reason
I am continuing to do research on structural priming to test the assumptions about prediction error-based learning in the deep learning model. Recently, I have started to examine the lexical boost as well.
|
| Strategy for Future Research Activity |
Now that the previous paper is almost done, I will start some new deep learning modeling work.
|
| Causes of Carryover |
I was not able to finish using my amount for this year.
|
