Explainable importance ranking of research paper (NVIDIA)
In this paper, we propose 2 parts of the work. First, we do research and evaluated 7 BERT (Bidirectional Encoder Representation from Transformers) models on citation intent classification task on scientific papers in medical and computer science fields, and proposed a method for data augmentation wh...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis-Master by Coursework |
| Language: | English |
| Published: |
Nanyang Technological University
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/154747 |
| _version_ | 1811695991030546432 |
|---|---|
| author | You, Yatao |
| author2 | Ponnuthurai Nagaratnam Suganthan |
| author_facet | Ponnuthurai Nagaratnam Suganthan You, Yatao |
| author_sort | You, Yatao |
| collection | NTU |
| description | In this paper, we propose 2 parts of the work. First, we do research and evaluated 7 BERT (Bidirectional Encoder Representation from Transformers) models on citation intent classification task on scientific papers in medical and computer science fields, and proposed a method for data augmentation which is able to improve all 7 models' performances. Second, we build a citation network using a citation relationship dataset we extracted and propose a new Leaky PageRank algorithm, which can perform on nodes of higher dimensions, and has managed to rank papers with high explainability. We have also compared this new method with the original weighted PageRank method and have proved in mathematics that our new method can solve problems which original one cannot. |
| first_indexed | 2024-10-01T07:32:15Z |
| format | Thesis-Master by Coursework |
| id | ntu-10356/154747 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T07:32:15Z |
| publishDate | 2022 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1547472023-07-04T17:42:23Z Explainable importance ranking of research paper (NVIDIA) You, Yatao Ponnuthurai Nagaratnam Suganthan School of Electrical and Electronic Engineering NVIDIA EPNSugan@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Document and text processing Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence In this paper, we propose 2 parts of the work. First, we do research and evaluated 7 BERT (Bidirectional Encoder Representation from Transformers) models on citation intent classification task on scientific papers in medical and computer science fields, and proposed a method for data augmentation which is able to improve all 7 models' performances. Second, we build a citation network using a citation relationship dataset we extracted and propose a new Leaky PageRank algorithm, which can perform on nodes of higher dimensions, and has managed to rank papers with high explainability. We have also compared this new method with the original weighted PageRank method and have proved in mathematics that our new method can solve problems which original one cannot. Master of Science (Computer Control and Automation) 2022-01-06T07:19:38Z 2022-01-06T07:19:38Z 2021 Thesis-Master by Coursework You, Y. (2021). Explainable importance ranking of research paper (NVIDIA). Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/154747 https://hdl.handle.net/10356/154747 en ISM-DISS-02543 application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Computer science and engineering::Computing methodologies::Document and text processing Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence You, Yatao Explainable importance ranking of research paper (NVIDIA) |
| title | Explainable importance ranking of research paper (NVIDIA) |
| title_full | Explainable importance ranking of research paper (NVIDIA) |
| title_fullStr | Explainable importance ranking of research paper (NVIDIA) |
| title_full_unstemmed | Explainable importance ranking of research paper (NVIDIA) |
| title_short | Explainable importance ranking of research paper (NVIDIA) |
| title_sort | explainable importance ranking of research paper nvidia |
| topic | Engineering::Computer science and engineering::Computing methodologies::Document and text processing Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence |
| url | https://hdl.handle.net/10356/154747 |
| work_keys_str_mv | AT youyatao explainableimportancerankingofresearchpapernvidia |