VGU RESEARCH REPOSITORY
Please use this identifier to cite or link to this item:
https://epub.vgu.edu.vn/handle/dlibvgu/988
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Duong Thanh Hung | en_US |
dc.date.accessioned | 2021-03-08T08:10:24Z | - |
dc.date.accessioned | 2021-03-08T08:10:27Z | - |
dc.date.available | 2021-03-08T08:10:24Z | - |
dc.date.available | 2021-03-08T08:10:27Z | - |
dc.date.issued | 2020 | - |
dc.identifier.uri | http://epub.vgu.edu.vn/handle/dlibvgu/988 | - |
dc.description.abstract | In this thesis, we set out to investigate the task of relation extraction. In particular, we only concern about the relation classification step for binary relations. We conducted experiments with various settings, using BERT as the word representation. We also tested the idea of assigning "no relation" detection to a separate classifier. Overall, the single-classifier architecture yields the best performance. On the SemEval 2010 Task 8 dataset, it achieved the F1 score of 90.12%, and on the GDS dataset, it reached the average precision score of 85.05%. The duo classifier architecture does not fall far behind (89.98% F1 on the SemEval dataset) | en_US |
dc.language.iso | en | en_US |
dc.subject | Natural language processing | en_US |
dc.subject | Relation extraction | en_US |
dc.subject | Supervised machine learning | en_US |
dc.subject | SemEval 2010 Task 8 dataset | en_US |
dc.title | Relation extraction from text using supervised machine learning | en_US |
dc.type | Thesis | en_US |
item.grantfulltext | open | - |
item.fulltext | With Fulltext | - |
item.languageiso639-1 | other | - |
Appears in Collections: | Computer Science (CS) Computer Science (CS) |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Relation extraction from text using supervised machine learning.pdf | 2.96 MB | Adobe PDF | View/Open |
Items are protected by © Copyright of Vietnamese - German University Library