2000 character limit reached
Large Language Models Meet Knowledge Graphs to Answer Factoid Questions (2310.02166v1)
Published 3 Oct 2023 in cs.CL
Abstract: Recently, it has been shown that the incorporation of structured knowledge into LLMs significantly improves the results for a variety of NLP tasks. In this paper, we propose a method for exploring pre-trained Text-to-Text LLMs enriched with additional information from Knowledge Graphs for answering factoid questions. More specifically, we propose an algorithm for subgraphs extraction from a Knowledge Graph based on question entities and answer candidates. Then, we procure easily interpreted information with Transformer-based models through the linearization of the extracted subgraphs. Final re-ranking of the answer candidates with the extracted information boosts Hits@1 scores of the pre-trained text-to-text LLMs by 4-6%.
- Dbpedia: A nucleus for a web of open data. The Semantic Web, page 722–735.
- Multilingual autoregressive entity linking.
- Introduction to neural network-based question answering over knowledge graphs. WIREs Data Mining Knowl. Discov., 11(3).
- KBQA: learning question answering over QA corpora and knowledge bases. CoRR, abs/1903.02419.
- Question answering benchmarks for wikidata. In Proceedings of the ISWC 2017 Posters & Demonstrations and Industry Tracks co-located with 16th International Semantic Web Conference (ISWC 2017), Vienna, Austria, October 23rd - to - 25th, 2017.
- Lc-quad 2.0: A large dataset for complex question answering over wikidata and dbpedia. In The Semantic Web - ISWC 2019 - 18th International Semantic Web Conference, Auckland, New Zealand, October 26-30, 2019, Proceedings, Part II, volume 11779 of Lecture Notes in Computer Science, pages 69–78. Springer.
- A survey on complex knowledge base question answering: Methods, challenges and solutions. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21, pages 4483–4491. International Joint Conferences on Artificial Intelligence Organization. Survey Track.
- Key-value memory networks for directly reading documents. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 1400–1409, Austin, Texas. Association for Computational Linguistics.
- Never-ending learning. Commun. ACM, 61(5):103–115.
- Systematic review of question answering over knowledge bases. IET Softw., 16(1):1–13.
- Aleksandr Perevalov and Andreas Both. 2020. Augmentation-based answer type classification of the SMART dataset. In Proceedings of the SeMantic AnsweR Type prediction task (SMART) at ISWC 2020 Semantic Web Challenge co-located with the 19th International Semantic Web Conference (ISWC 2020), Virtual Conference, November 5th, 2020, volume 2774 of CEUR Workshop Proceedings, pages 1–9. CEUR-WS.org.
- A system for answering simple questions in multiple languages. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), pages 524–537, Toronto, Canada. Association for Computational Linguistics.
- How much knowledge can you pack into the parameters of a language model? In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020, Online, November 16-20, 2020, pages 5418–5426. Association for Computational Linguistics.
- Rubq 2.0: An innovated russian question answering dataset. In The Semantic Web - 18th International Conference, ESWC 2021, Virtual Event, June 6-10, 2021, Proceedings, volume 12731 of Lecture Notes in Computer Science, pages 532–547. Springer.
- End-to-end entity resolution and question answering using differentiable knowledge graphs. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 4193–4200, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Distilbert, a distilled version of BERT: smaller, faster, cheaper and lighter. CoRR, abs/1910.01108.
- Improving multi-hop question answering over knowledge graphs using knowledge base embeddings. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4498–4507, Online. Association for Computational Linguistics.
- Mintaka: A complex, natural, and multilingual dataset for end-to-end question answering. In Proceedings of the 29th International Conference on Computational Linguistics, pages 1604–1619, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
- Mpnet: Masked and permuted pre-training for language understanding. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual.
- PullNet: Open domain question answering with iterative retrieval on knowledge bases and text. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 2380–2390, Hong Kong, China. Association for Computational Linguistics.
- Diverse beam search: Decoding diverse solutions from neural sequence models.
- Denny Vrandečić and Markus Krötzsch. 2014. Wikidata: A free collaborative knowledgebase. Commun. ACM, 57(10):78–85.
- Path-aware multi-hop question answering over knowledge graph embedding. In 2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI), pages 459–466.
- Hic-kgqa: Improving multi-hop question answering over knowledge graph via hypergraph and inference chain. Knowledge-Based Systems, page 110810.
- Do transformers really perform badly for graph representation? In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual, pages 28877–28888.
- A review of deep learning in question answering over knowledge bases. AI Open, 2:205–215.
- Greaselm: Graph reasoning enhanced language models for question answering. CoRR, abs/2201.08860.
- Pretrain-kge: Learning knowledge representation from pretrained language models. In Findings of the Association for Computational Linguistics: EMNLP 2020, Online Event, 16-20 November 2020, volume EMNLP 2020 of Findings of ACL, pages 259–266. Association for Computational Linguistics.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.
