Skripsi
KEYPHRASE EXTRACTION MENGGUNAKAN PRETRAINED LANGUAGE MODEL ROBERTA DAN POSITION AWARE GRAPH
Searching for the desired scientific journal from the many published journals is currently a challenge for researchers because it takes a lot of time. Therefore, the use of keyphrases or keywords that represent the content of scientific journals is needed as a solution to save search time. The keyphrase extraction process is carried out to obtain relevant keyphrases. One of the keyphrase extraction methods is Position Aware Graph combined with a pretrained language model called RoBERTa to represent language vectors. This research aims to create a keyphrase extraction system using Pretrained Language Model RoBERTa and Position Aware Graph. In the test, 100 datasets containing title and abstract data of scientific journals were used. The test results show that the best configuration is keyphrase extraction with the selection of 10 selected keyphrases with an average f1-score value of 0.1434.
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2407001959 | T142121 | T1421212024 | Central Library (REFERENCES) | Available but not for loan - Not for Loan |
No other version available