BERTologyNavigator: Advanced Question Answering with BERT-based Semantics
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914643962757120 |
|---|---|
| author | Rajpal, Shreya Usbeck, Ricardo |
| author_facet | Rajpal, Shreya Usbeck, Ricardo |
| contents | The development and integration of knowledge graphs and language models has significance in artificial intelligence and natural language processing. In this study, we introduce the BERTologyNavigator -- a two-phased system that combines relation extraction techniques and BERT embeddings to navigate the relationships within the DBLP Knowledge Graph (KG). Our approach focuses on extracting one-hop relations and labelled candidate pairs in the first phases. This is followed by employing BERT's CLS embeddings and additional heuristics for relation selection in the second phase. Our system reaches an F1 score of 0.2175 on the DBLP QuAD Final test dataset for Scholarly QALD and 0.98 F1 score on the subset of the DBLP QuAD test dataset during the QA phase. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_09553 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | BERTologyNavigator: Advanced Question Answering with BERT-based Semantics Rajpal, Shreya Usbeck, Ricardo Computation and Language Artificial Intelligence I.2.4; I.2.7 The development and integration of knowledge graphs and language models has significance in artificial intelligence and natural language processing. In this study, we introduce the BERTologyNavigator -- a two-phased system that combines relation extraction techniques and BERT embeddings to navigate the relationships within the DBLP Knowledge Graph (KG). Our approach focuses on extracting one-hop relations and labelled candidate pairs in the first phases. This is followed by employing BERT's CLS embeddings and additional heuristics for relation selection in the second phase. Our system reaches an F1 score of 0.2175 on the DBLP QuAD Final test dataset for Scholarly QALD and 0.98 F1 score on the subset of the DBLP QuAD test dataset during the QA phase. |
| title | BERTologyNavigator: Advanced Question Answering with BERT-based Semantics |
| topic | Computation and Language Artificial Intelligence I.2.4; I.2.7 |
| url | https://arxiv.org/abs/2401.09553 |