Abstract
Entity linking is an essential part of analytical systems for question answering on knowledge graphs (KGQA). The mentioned entity has to be spotted in the text and linked to the correct resource in the knowledge graph (KG). With this paper, we present our approach on entity linking using the abstract meaning representation (AMR) of the question to spot the surface forms of entities. We re-trained AMR models with automatically generated training data. Based on these models, we extract surface forms and map them to an entity dictionary of the desired KG. For the disambiguation process, we evaluated different options and configurations on QALD-9 and LC-QuaD 2.0. The results of the best performing configurations outperform existing entity linking approaches.
N. Steinmetz—Work was done while at TU Ilmenau.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Unfortunately, the Lexicalization dataset is not available anymore.
- 2.
- 3.
- 4.
- 5.
The newest model is trained on 2016 LDC training data.
- 6.
as of December 2022.
- 7.
- 8.
- 9.
- 10.
- 11.
- 12.
cf. the training dataset of the SMART task challenge 2022: https://smart-task.github.io/2022/.
- 13.
- 14.
- 15.
The SMATCH score for BART Large is stated as 0.837 trained on LDC AMR 3.0.
- 16.
- 17.
instructions on how to use the models with amrlib can be found here: https://github.com/bjascob/amrlib-models.
- 18.
which would not be helpful for that disambiguation case.
- 19.
- 20.
- 21.
The authors do not wish to use the JSON web service for evaluation comparison and it also responses with HTTP 404 as of December 10th 2022.
References
Bender, E.M., Koller, A.: Climbing towards NLU: on meaning, form, and understanding in the age of data. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 5185–5198. Association for Computational Linguistics (2020). https://doi.org/10.18653/v1/2020.acl-main.463
Delpeuch, A.: OpenTapioca: Lightweight entity linking for Wikidata. CoRR abs/1904.09131 (2019). http://arxiv.org/abs/1904.09131
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding (2018). https://doi.org/10.48550/ARXIV.1810.04805
Diomedi, D., Hogan, A.: Entity linking and filling for question answering over knowledge graphs. In: Natural Language Interfaces for the Web of Data (NLIWOD) Workshop (2022)
Dubey, M., Banerjee, D., Abdelkawi, A., Lehmann, J.: LC-QuAD 2.0: a large dataset for complex question answering over Wikidata and DBpedia. In: Cruz, I., et al. (eds.) ISWC 2019. LNCS, vol. 11779, pp. 69–78. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-30796-7_5
Ferragina, P., Scaiella, U.: Tagme: on-the-fly annotation of short text fragments (by Wikipedia entities). In: Proceedings of the 19th ACM International Conference on Information and Knowledge Management (CIKM 2010), pp. 1625–1628. Association for Computing Machinery, New York (2010). https://doi.org/10.1145/1871437.1871689
Ferragina, P., Scaiella, U.: Fast and accurate annotation of short texts with Wikipedia pages. IEEE Softw. 29(1), 70–75 (2012). https://doi.org/10.1109/MS.2011.122
Jiang, H., et al.: LNN-EL: a neuro-symbolic approach to short-text entity linking. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, vol. 1, pp. 775–787. Association for Computational Linguistics (2021). https://doi.org/10.18653/v1/2021.acl-long.64
Kapanipathi, P., et al.: Leveraging abstract meaning representation for knowledge base question answering. In: Zong, C., Xia, F., Li, W., Navigli, R. (eds.) Findings of the Association for Computational Linguistics (ACL/IJCNLP 2021). Online Event, 1–6 August 2021. Findings of ACL, vol. ACL/IJCNLP 2021, pp. 3884–3894. Association for Computational Linguistics (2021). https://doi.org/10.18653/v1/2021.findings-acl.339
Lee, Y.S., Astudillo, R., Thanh Lam, H., Naseem, T., Florian, R., Roukos, S.: Maximum Bayes Smatch ensemble distillation for AMR parsing. In: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 5379–5392. Association for Computational Linguistics, Seattle (2022). https://doi.org/10.18653/v1/2022.naacl-main.393
Lewis, M., et al.: BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension (2019). https://doi.org/10.48550/ARXIV.1910.13461
Li, B.Z., Min, S., Iyer, S., Mehdad, Y., Yih, W.T.: Efficient one-pass end-to-end entity linking for questions. In: EMNLP (2020)
Mendes, P.N., Jakob, M., García-Silva, A., Bizer, C.: DBpedia spotlight: shedding light on the web of documents. In: Proceedings of the 7th International Conference on Semantic Systems (I-Semantics 2011), pp. 1–8. Association for Computing Machinery, New York (2011). https://doi.org/10.1145/2063518.2063519
Milne, D., Witten, I.H.: Learning to link with Wikipedia. In: Proceedings of the 17th ACM Conference on Information and Knowledge Management (CIKM 2008), pp. 509–518. Association for Computing Machinery, New York (2008). https://doi.org/10.1145/1458082.1458150
Neelam, S., et al.: SYGMA: system for generalizable modular question answering overknowledge bases. CoRR abs/2109.13430 (2021). https://arxiv.org/abs/2109.13430
Sakor, A., Singh, K., Patel, A., Vidal, M.E.: Falcon 2.0: an entity and relation linking tool over Wikidata. In: Proceedings of the 29th ACM International Conference on Information and Knowledge Management (CIKM 2020), pp. 3141–3148. Association for Computing Machinery, New York (2020). https://doi.org/10.1145/3340531.3412777
Shivashankar, K., Benmaarouf, K., Steinmetz, N.: From graph to graph: AMR to SPARQL. In: Proceedings of the 7th Natural Language Interfaces for the Web of Data (NLIWoD) co-located with the 19th European Semantic Web Conference (ESWC 2022), Hersonissos, Greece, 29th May 2022. CEUR Workshop Proceedings, vol. 3196 (2022). http://ceur-ws.org/Vol-3196
Steinmetz, N.: Context-aware semantic analysis of video metadata. Ph.D. thesis, University of Potsdam (2014). http://opus.kobv.de/ubp/volltexte/2014/7055/
Steinmetz, N., Sattler, K.U.: What is in the KGQA benchmark datasets? Survey on challenges in datasets for question answering on knowledge graphs. J. Data Semant. 10(3–4), 241–265 (2021). https://doi.org/10.1007/s13740-021-00128-9
Usbeck, R., Gusmita, R.H., Ngomo, A.N., Saleem, M.: 9th challenge on question answering over linked data. In: Choi, K., et al. (eds.) Joint proceedings of the 4th Workshop on Semantic Deep Learning (SemDeep-4) and NLIWoD4: Natural Language Interfaces for the Web of Data and 9th Question Answering over Linked Data challenge (QALD-9) co-located with 17th International Semantic Web Conference (ISWC 2018), Monterey, California, United States of America, 8th–9th October 2018. CEUR Workshop Proceedings, vol. 2241, pp. 58–64 (2018). http://ceur-ws.org/Vol-2241/paper-06.pdf
Yosef, M.A., Hoffart, J., Bordino, I., Spaniol, M., Weikum, G.: AIDA: an online tool for accurate disambiguation of named entities in text and tables. Proc. VLDB Endow. 4(12), 1450–1453 (2011). https://doi.org/10.14778/3402755.3402793
Acknowledgement
The author wants to thank Khaoula Benmaarouf and Kanchan Shivashankar for their help in preparing some of the data utilized for this paper.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Steinmetz, N. (2023). Entity Linking for KGQA Using AMR Graphs. In: Pesquita, C., et al. The Semantic Web. ESWC 2023. Lecture Notes in Computer Science, vol 13870. Springer, Cham. https://doi.org/10.1007/978-3-031-33455-9_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-33455-9_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-33454-2
Online ISBN: 978-3-031-33455-9
eBook Packages: Computer ScienceComputer Science (R0)