Summary of Hybrid-squad: Hybrid Scholarly Question Answering Dataset, by Tilahun Abedissa Taffa et al.
Hybrid-SQuAD: Hybrid Scholarly Question Answering Dataset
by Tilahun Abedissa Taffa, Debayan Banerjee, Yaregal Assabie, Ricardo Usbeck
First submitted to arxiv on: 3 Dec 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 Existing Scholarly Question Answering (QA) methods focus on homogeneous data sources, either text or Knowledge Graphs (KGs). However, scholarly information often spans heterogeneous sources, requiring QA systems that integrate information from multiple sources. To address this challenge, we introduce Hybrid-SQuAD (Hybrid Scholarly Question Answering Dataset), a novel large-scale QA dataset designed to facilitate answering questions incorporating both text and KG facts. The dataset consists of 10.5K question-answer pairs generated by a large language model, leveraging the KGs DBLP and SemOpenAlex alongside corresponding text from Wikipedia. We propose a RAG-based baseline hybrid QA model, achieving an exact match score of 69.65 on the Hybrid-SQuAD test set. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Right now, computer systems can only answer questions about simple things like what’s in a book or who wrote a paper. But sometimes we need to answer more complicated questions that involve different types of information from multiple sources. To make this easier, we created a new database called Hybrid-SQuAD with thousands of question-answer pairs. We used big computer models and special knowledge graphs to generate these questions. Our goal is to create systems that can answer complex questions by combining information from different places like Wikipedia and other databases. |
Keywords
» Artificial intelligence » Large language model » Question answering » Rag
