Summary of Bertologynavigator: Advanced Question Answering with Bert-based Semantics, by Shreya Rajpal (1 et al.
BERTologyNavigator: Advanced Question Answering with BERT-based Semantics
by Shreya Rajpal, Ricardo Usbeck
First submitted to arxiv on: 17 Jan 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The BERTologyNavigator is a two-phased system that leverages relation extraction techniques and BERT embeddings to navigate relationships within the DBLP Knowledge Graph (KG). This approach focuses on extracting one-hop relations and labelled candidate pairs in the first phase, followed by employing BERT’s CLS embeddings and additional heuristics for relation selection in the second phase. The system achieves an F1 score of 0.2175 on the DBLP QuAD Final test dataset for Scholarly QALD and 0.98 F1 score on the QA subset. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The BERTologyNavigator is a tool that helps us understand how things are connected in a big library of information called the DBLP Knowledge Graph. It uses two steps to find these connections: first, it finds simple relationships between things, then it uses special language models and rules to pick the most important ones. This system does a pretty good job at finding the right relationships, with an F1 score of 0.2175 for one type of question-answering task and 0.98 for another. |
Keywords
» Artificial intelligence » Bert » F1 score » Knowledge graph » Question answering
