ULYSSES: Automated FreqUentLY ASked QueStions for KnowlEdge GraphS
Source abstract
Abstract
The exponential growth of Knowledge Graphs necessitates effective and efficient methods for their exploration and understanding. Frequently Asked Questions (FAQ) is a service that typically presents a list of questions and answers related to a specific topic, and which is intended to help people understand that topic. Although FAQ has already shown its value on large websites and is widely used, to the best of our knowledge it has not yet been exploited for Knowledge Graphs. In this paper, we present ULYSSES, the first system for automatically constructing FAQ lists for large Knowledge Graphs. Our method consists of three key steps. First, we select the most frequent queries by exploiting the available query logs. Next, we answer the selected queries, using the original graph. Finally, we construct textual descriptions of both the queries and the corresponding answers, exploring state-of-the-art transformer models, i.e., ChatGPT 3.5 and Gemini 1.5 Pro. We evaluate the results of each model, using a human-constructed FAQ list, contributing a unique dataset to the domain and showing the benefits of our approach.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Graph Neural Networks · Topic Modeling · Data Quality and Management
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Electrical and Computer Engineering, Hellenic Mediterranean University (HMU), 71309 Heraklion, Greece
Institute of Computer Science, Foundation for Research and Technology-Hellas (FORTH), 70013 Heraklion, Greece
Computer Science Department, University of Crete, 70013 Heraklion, Greece
References (34)
Show source-provided references
1. Summarizing semantic graphs: A survey10.1007/s00778-018-0528-3 ↗
2. Nascimento, M.A. (2006, January 16–20). Extracting and Searching Useful Information Available on Web FAQs. Proceedings of the XXI Simpósio Brasileiro de Banco de Dados, Florianópolis, SC, Brasil. Anais/Proceedings.
3. Trouli, G.E., Papadakis, N., and Kondylakis, H. (2024). Constructing Semantic Summaries Using Embeddings. Information, 15.10.3390/info15040238 ↗
4. Vassiliou, G., Papadakis, N., and Kondylakis, H. (2023, January 6–10). iSummary: Demonstrating Workload-based, Personalized Summaries for Knowledge Graphs. Proceedings of the ISWC 2023 Posters and Demos: 22nd International Semantic Web Conference, Athens, Greece. Available online: https://ceur-ws.org/Vol-3632/ISWC2023_paper_435.pdf.
5. Exploring RDFS KBs Using Summaries10.1007/978-3-030-00671-6_16 ↗
6. A Novel Approach to Visualizing and Navigating Ontologies10.1007/978-3-642-25073-6_30 ↗
7. Summarizing Vocabularies in the Global Semantic Web10.1007/s11390-009-9212-9 ↗
8. iSummary: Workload-Based, Personalized Summaries for Knowledge Graphs
9. Zhu, Q., Zhu, X., Tu, Y., Xu, Z., and Kumar, A. (2021, January 6–7). WBSum: Workload-based Summaries for RDF/S KBs. Proceedings of the SSDBM 2021: 33rd International Conference on Scientific and Statistical Database Management, Tampa, FL, USA.
10. Knowledge Graphs Querying10.1145/3615952.3615956 ↗
11. Core techniques of question answering systems over knowledge bases: A survey10.1007/s10115-017-1100-y ↗
12. A template-based approach for question answering over knowledge bases10.1007/s10115-023-01966-8 ↗
13. Barrett, R., Cummings, R., Agichtein, E., and Gabrilovich, E. (2017, January 3–7). Neural Network-based Question Answering over Knowledge Graphs on Word and Character Level. Proceedings of the 26th International Conference on World Wide Web, WWW 2017, Perth, Australia.
14. Auto-FAQ-Gen: Automatic Frequently Asked Questions Generation
15. Gurevych, I., and Miyao, Y. (2018, January 15–20). Harvesting Paragraph-level Question-Answer Pairs from Wikipedia. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018, Melbourne, Australia. Volume 1: Long Papers.
16. Willis, A., Davis, G.M., Ruan, S., Manoharan, L., Landay, J.A., and Brunskill, E. (2019, January 24–25). Key Phrase Extraction for Generating Educational Question-Answer Pairs. Proceedings of the Sixth ACM Conference on Learning @ Scale, L@S 2019, Chicago, IL, USA.10.1145/3330430.3333636 ↗
17. Kumar, A., Kharadi, A., Singh, D., and Kumari, M. (2021, January 2–4). Automatic question-answer pair generation using Deep Learning. Proceedings of the 2021 Third International Conference on Inventive Research in Computing Applications (ICIRCA), Coimbatore, India.10.1109/ICIRCA51532.2021.9544654 ↗
18. Kabbara, J., Lin, H., Paullada, A., and Vamvas, J. (2021, January 5–10). Improving the Robustness of QA Models to Challenge Sets with Variational Question-Answer Pair Generation. Proceedings of the ACL-IJCNLP 2021 Student Research Workshop, ACL 2021, Online.
19. Hall, J.G., Kaindl, H., Lavazza, L., Buchgeher, G., and Takaki, O. (2010, January 22–27). A FAQ Finding Process in Open Source Project Forums. Proceedings of the Fifth International Conference on Software Engineering Advances, ICSEA 2010, Nice, France.
20. Hu, X., Barnes, T., Hershkovitz, A., and Paquette, L. (2017, January 25–28). Inferring Frequently Asked Questions from Student Question Answering Forums. Proceedings of the 10th International Conference on Educational Data Mining, EDM 2017, Wuhan, China.
21. Bihani, A., Ullman, J.D., and Paepcke, A. (2018). FAQtor: Automatic FAQ Generation Using Online Forums, Stanford InfoLab. Technical Report.
22. Zhao, H., Liu, Y., Hou, A., and Gu, J. (2022, January 9–12). Knowledge Graph based Question Pair Matching for Domain-Oriented FAQ System. Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics, SMC 2022, Prague, Czech Republic.10.1109/SMC53654.2022.9945243 ↗
23. FAQ-Based Question Answering via Knowledge Anchors
24. BB-KBQA: BERT-Based Knowledge Base Question Answering
25. Tseng, W., Wu, C., Hsu, Y., and Chen, B. (2021, January 14–17). FAQ Retrieval using Question-Aware Graph Convolutional Network and Contextualized Language Model. Proceedings of the Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2021, Tokyo, Japan.
26. W3C (2024, August 01). Resource Description Framework. Available online: http://www.w3.org/RDF/.
27. W3C (2024, August 01). Recommendation, SPARQL Query Language for RDF. Available online: https://www.w3.org/TR/rdf-sparql-query/.
28. An analytical study of large SPARQL query logs10.1007/s00778-019-00558-9 ↗
29. Getting the Most Out of Wikidata: Semantic Technology Usage in Wikipedia’s Knowledge Graph10.1007/978-3-030-00668-6_23 ↗
30. Anil, R., Borgeaud, S., Wu, Y., Alayrac, J., Yu, J., Soricut, R., Schalkwyk, J., Dai, A.M., Hauth, A., and Millican, K. (2023). Gemini: A Family of Highly Capable Multimodal Models. arXiv.
31. Fine-Tuned T5 for Abstractive Summarization10.23940/ijpe.21.10.p8.900906 ↗
32. Venkataramana, A., Srividya, K., and Cristin, R. (2022, January 16–17). Abstractive Text Summarization Using BART. Proceedings of the 2022 IEEE 2nd Mysore Sub Section International Conference (MysuruCon), Mysuru, India.10.1109/MysuruCon55714.2022.9972639 ↗
33. Lin, C.Y. (2004). Rouge: A package for automatic evaluation of summaries. Text Summarization Branches Out, Association for Computational Linguistics.
34. (2024, February 29). What is the ROUGE Score (Recall-Oriented Understudy for Gisting Evaluation)?. Available online: https://klu.ai/glossary/rouge-score.