Elamur Research⌕
☰
home / papers / 2021 / Leveraging Abstract Meaning Representation for Knowledge Base Question Answering

Leveraging Abstract Meaning Representation for Knowledge Base Question Answering

Paper · 2021 · Pavan Kapanipathi, Ibrahim Abdelaziz, Srinivas Ravishankar et al.

Summary

The paper addresses knowledge base question answering (KBQA). Here a system must convert a natural-language question into a structured query, for example SPARQL, and find the answer among the facts in the knowledge base. The main challenges are complex multi-hop questions, the need for logical reasoning, and the lack of large datasets of question–query pairs for end-to-end training. Researchers at IBM Research propose NSQA, a modular system. First, the question is parsed into an Abstract Meaning Representation (AMR) graph. Next, a simple algorithm searches for paths between the unknown node and the nodes of already linked entities and, on this basis, constructs logical queries aligned with the knowledge base. Finally, the neuro-symbolic reasoner Logical Neural Networks (LNN) finds the answer. Each module is trained separately on its own subtask, so no end-to-end data is needed. On two DBpedia-based datasets, QALD-9 and LC-QuAD 1.0, NSQA achieves state-of-the-art results. The work shows that a general-purpose semantic parser makes it possible to build KBQA systems without large amounts of task-specific annotated data.

Key points

  • The authors describe NSQA as the first AMR-based KBQA system. Parsing is done with the transition-based stack-Transformer parser, which explicitly aligns the words of the question with AMR nodes.
  • Entities are recognized by a BERT model and linked to DBpedia by the BLINK module. A separate module handles relation linking.
  • Selecting the shortest paths from the amr-unknown node to the entities solves two problems. First, AMR predicates have n arguments, whereas knowledge base relations are binary. Second, the structure and granularity of the two graphs differ; for example, a single relation dbo:currency may correspond to a combination of several nodes and edges in AMR.
  • AMR parsing quality directly affects system quality. On the LC-QuAD 1.0 dev set, a 1.4% gain in Smatch raised the overall result by 1.2%. The best AMR parsers already exceed 84% F-measure.
  • The authors acknowledge limitations: AMR errors propagate further down the pipeline (inter-annotator agreement is only about 83%), and Smatch is poorly suited as a training objective for KBQA. In future work, they plan to add temporal reasoning and robustness to incomplete and inconsistent knowledge bases.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🏢IBMArmonk · United States139 works · 70,691 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 works

🧭 Topics 3Research subjects and languages the work is about.Question answering · 441 worksKnowledge graphs & ontologies · 192 worksSemantic parsing & meaning representation · 185 works

💡 Concepts 1Key ideas and methods explained on our concept pages.Semantics · 57 works

Cite

Cite as Pavan Kapanipathi, Ibrahim Abdelaziz, Srinivas Ravishankar, Salim Roukos, Alexander Gray, Ramón Fernandez Astudillo, Maria Chang, Cristina Cornelio, Saswati Dana, Achille Fokoue, Dinesh Garg, Alfio Gliozzo, Sairam Gurajada, Hima Karanam, Naweed Khan, Dinesh Khandelwal, Young-Suk Lee, Yunyao Li, Francois Luus, Ndivhuwo Makondo, Nandana Mihindukulasooriya, Tahira Naseem, Sumit Neelam, Lucian Popa, Revanth Gangi Reddy, Ryan Riegel, Gaetano Rossiello, Udit Sharma, G P Shrivatsa Bhargav and Mo Yu. 2021. Leveraging Abstract Meaning Representation for Knowledge Base Question Answering. Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2021.findings-acl.339 · arXiv 2012.01707

@inproceedings{kapanipathi2021leveraging,
  title = {{Leveraging Abstract Meaning Representation for Knowledge Base Question Answering}},
  author = {Pavan Kapanipathi, Ibrahim Abdelaziz, Srinivas Ravishankar, Salim Roukos, Alexander Gray, Ramón Fernandez Astudillo, Maria Chang, Cristina Cornelio, Saswati Dana, Achille Fokoue, Dinesh Garg, Alfio Gliozzo, Sairam Gurajada, Hima Karanam, Naweed Khan, Dinesh Khandelwal, Young-Suk Lee, Yunyao Li, Francois Luus, Ndivhuwo Makondo, Nandana Mihindukulasooriya, Tahira Naseem, Sumit Neelam, Lucian Popa, Revanth Gangi Reddy, Ryan Riegel, Gaetano Rossiello, Udit Sharma, G P Shrivatsa Bhargav and Mo Yu},
  booktitle = {Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021},
  year = {2021},
  doi = {10.18653/v1/2021.findings-acl.339},
  eprint = {2012.01707},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.18653/v1/2021.findings-acl.339}
}

References

40 references, 5 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Ibrahim Abdelaziz, Srinivas Ravishankar, Pavan Kapanipathi, Salim Roukos, and Alexander Gray. 2021. A semantic parsing and reasoning-based approach to knowledge base question answering. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 15985–15987. find
  2. Ramón Fernandez Astudillo, Miguel Ballesteros, Tahira Naseem, Austin Blodgett, and Radu Florian. 2020. Transition-based parsing with stack-transformers. In Findings of the Association for Computational Linguistics: EMNLP 2020, page 1001–1007. find
  3. Laura Banarescu, Claire Bonial, Shu Cai, Madalina Georgescu, Kira Griffitt, Ulf Hermjakob, Kevin Knight, Philipp Koehn, Martha Palmer, and Nathan Schneider. 2013. Abstract meaning representation for sembanking. In Proceedings of the 7th linguistic annotation workshop and interoperability with discourse, pages 178–186.
  4. Hannah Bast and Elmar Haussmann. 2015. More accurate question answering on freebase. In Proceedings of the 24th ACM International on Conference on Information and Knowledge Management, pages 1431–1440. find
  5. Jonathan Berant, Andrew Chou, Roy Frostig, and Percy Liang. 2013. Semantic parsing on freebase from question-answer pairs. In Proceedings of the 2013 conference on empirical methods in natural language processing, pages 1533–1544.
  6. Michele Bevilacqua, Rexhina Blloshmi, and Roberto Navigli. 2021. One SPRING to rule them both: Symmetric AMR semantic parsing and generation without a complex pipeline. In Proceedings of AAAI. Conclusion and Future Work To the best of our knowledge, NSQA is the first system that successfully harnesses a generic semantic parser, particularly AMR, for a KBQA task. Our path-based approach to map AMR to the underlying KG such as DBpedia is first of its kind Nikita Bhutani, Xinyi Zheng, and H V Jagadish. 2019. Learning to answer complex questions over knowledge bases with query composition. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management, CIKM ’19, page 739–748, New York, NY, USA. Association for Computing Machinery. ↗
  7. Antoine Bordes, Nicolas Usunier, Sumit Chopra, and Jason Weston. 2015. Large-scale simple question answering with memory networks. arXiv preprint arXiv:1506.02075. ↗
  8. Shu Cai and Kevin Knight. 2013. Smatch: an evaluation metric for semantic feature structures. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 748–752. find
  9. Yongrui Chen, Huiying Li, Yuncheng Hua, and Guilin Qi. 2020. Formal query building with query structure prediction for complex question answering over knowledge base. In International Joint Conference on Artificial Intelligence (IJCAI). find
  10. William W Cohen, Haitian Sun, R Alex Hofer, and Matthew Siegler. 2020. Scalable neural methods for reasoning with a symbolic knowledge base. arXiv preprint arXiv:2002.06115. ↗
  11. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. BERT: pre-training of deep bidirectional transformers for language understanding. CoRR, abs/1810.04805. ↗
  12. Dennis Diefenbach, Andreas Both, Kamal Singh, and Pierre Maret. 2020. Towards a question answering system over the semantic web. Semantic Web, (Preprint):1–19. ↗
  13. Dennis Diefenbach, Kamal Singh, and Pierre Maret. 2017. Wdaqua-core0: A question answering component for the research community. In Semantic Web Evaluation Challenge, pages 84–89. Springer. find
  14. Bonnie Dorr, Nizar Habash, and David Traum. 1998. A thematic hierarchy for efficient generation from lexical-conceptual structure. In Conference of the Association for Machine Translation in the Americas, pages 333–343. Springer. ↗
  15. Mohnish Dubey, Debayan Banerjee, Abdelrahman Ab-delkawi, and Jens Lehmann. 2019. Lc-quad 2.0: A large dataset for complex question answering over wikidata and dbpedia. In The Semantic Web - ISWC 2019. find
  16. Paul R Kingsbury and Martha Palmer. 2002. From treebank to propbank. In LREC, pages 1989–1993. Citeseer.
  17. Young-Suk Lee, Ramón Fernandez Astuillo, Tahira Naseem, Revanth Reddy, Radu Florian, and Salim Roukos. 2020. Pushing the limits of amr parsing with self-learning. In Findings of the Association for Computational Linguistics: EMNLP 2020, page 3208–3214. find
  18. Shiqi Liang, Kurt Stockinger, Tarcisio Mendes de Farias, Maria Anisimova, and Manuel Gil. 2021. Querying knowledge graphs in natural language. Journal of Big Data, 8(1):1–23. ↗
  19. Gaurav Maheshwari, Priyansh Trivedi, Denis Lukovnikov, Nilesh Chakraborty, Asja Fischer, and Jens Lehmann. 2019. Learning to rank query graphs for complex question answering over knowledge graphs. In International semantic web conference, pages 487–504. Springer. find
  20. Giuseppe M Mazzeo and Carlo Zaniolo. 2016. Answering controlled natural language questions on rdf knowledge bases. In EDBT, pages 608–611. find
  21. Nandana Mihindukulasooriya, Gaetano Rossiello, Pavan Kapanipathi, Ibrahim Abdelaziz, Srinivas Ravishankar, Mo Yu, Alfio Gliozzo, Salim Roukos, and Alexander Gray. 2020. Leveraging Semantic Parsing for Relation Linking over Knowledge Bases. In Proceedings of the 19th International Semantic Web Conference (ISWC2020). find
  22. Tahira Naseem, Srinivas Ravishankar, Nandana Mihindukulasooriya, Ibrahim Abdelaziz, Young-Suk Lee, Pavan Kapanipathi, Salim Roukos, Alfio Gliozzo, and Alexander Gray. 2021. A semantics-aware transformer model of relation linking for knowledge base question answering. In ACL 2021. find
  23. Tahira Naseem, Abhishek Shah, Hui Wan, Radu Florian, Salim Roukos, and Miguel Ballesteros. 2019. Rewarding smatch: Transition-based amr parsing with reinforcement learning. arXiv preprint arXiv:1905.13370. ↗
  24. Hongyu Ren and Jure Leskovec. 2020. Beta embeddings for multi-hop logical reasoning in knowledge graphs. Advances in Neural Information Processing Systems, 33. ↗
  25. Ryan Riegel, Alexander Gray, Francois Luus, Naweed Khan, Ndivhuwo Makondo, Ismail Yunus Akhal-waya, Haifeng Qian, Ronald Fagin, Francisco Barahona, Udit Sharma, Shajith Ikbal, Hima Karanam, Sumit Neelam, Ankita Likhyani, and Santosh Srivastava. 2020. Logical neural networks. arXiv preprint arXiv:2006.13155. ↗
  26. Ahmad Sakor, Isaiah Onando Mulang’, Kuldeep Singh, Saeedeh Shekarpour, Maria Esther Vidal, Jens Lehmann, and Sören Auer. 2019. Old is gold: Linguistic driven approach for entity and relation linking of short text. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 2336–2346, Minneapolis, Minnesota. Association for Computational Linguistics. find
  27. Kuldeep Singh, Andreas Both, Arun Sethupat, and Saeedeh Shekarpour. 2018. Frankenstein: a platform enabling reuse of question answering components. In European Semantic Web Conference, pages 624–638. Springer. find
  28. Haitian Sun, Andrew O Arnold, Tania Bedrax-Weiss, Fernando Pereira, and William W Cohen. 2020. Faithful embeddings for knowledge base queries. Advances in Neural Information Processing Systems, 33. ↗
  29. Priyansh Trivedi, Gaurav Maheshwari, Mohnish Dubey, and Jens Lehmann. 2017. Lc-quad: A corpus for complex question answering over knowledge graphs. In ISWC 2017, pages 210–218. find
  30. Ricardo Usbeck, Axel-Cyrille Ngonga Ngomo, Bastian Haarmann, Anastasia Krithara, Michael Röder, and Giulio Napolitano. 2017. 7th open challenge on question answering over linked data (qald-7). In Semantic Web Evaluation Challenge, pages 59–69. Springer. find
  31. Svitlana Vakulenko, Javier David Fernandez Garcia, Axel Polleres, Maarten de Rijke, and Michael Cochez. 2019. Message passing for complex question answering over knowledge graphs. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management, pages 1431–1440. find
  32. Luke Zettlemoyer and Michael Collins. 2007. Online learning of relaxed ccg grammars for parsing to logical form. In Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), pages 678–687. find
  33. Weiguo Zheng and Mei Zhang. 2019. Question answering over knowledge graphs via structural query patterns. arXiv preprint arXiv:1910.09760. ↗
  34. Lei Zou, Ruizhe Huang, Haixun Wang, Jeffrey Xu Yu, Wenqiang He, and Dongyan Zhao. 2014. Natural language question answering over rdf: a graph data driven approach. In Proceedings of the 2014 ACM SIGMOD international conference on Management of data, pages 313–324. find
  35. Dekun Wu, Nana Nosirova, Hui Jiang, and Mingbin Xu. 2019a. A general fofe-net framework for simple and effective question answering over knowledge bases. arXiv preprint arXiv:1903.12356. ↗
  36. Ledell Wu, Fabio Petroni, Martin Josifoski, Sebastian Riedel, and Luke Zettlemoyer. 2019b. Zero-shot entity linking with dense entity retrieval. ArXiv, abs/1911.03814. ↗
  37. Kun Xu, Yuxuan Lai, Yansong Feng, and Zhiguo Wang. 2019. Enhancing key-value memory neural networks for knowledge based question answering. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 2937– 2947. find
  38. Kun Xu, Lingfei Wu, Zhiguo Wang, Mo Yu, Liwei Chen, and Vadim Sheinin. 2018. Exploiting rich syntactic information for semantic parsing with graph-to-sequence model. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 918–924. ↗
  39. Xuchen Yao and Benjamin Van Durme. 2014. Information extraction over structured data: Question answering with freebase. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 956–966. find
  40. Mo Yu, Wenpeng Yin, Kazi Saidul Hasan, Cicero dos Santos, Bing Xiang, and Bowen Zhou. 2017. Improved neural relation detection for knowledge base question answering. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 571– 581. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/kapanipathi-2021-leveraging-abstract-meaning-representation-knowledge/