Abstract
Entity linking (EL) in written language domains has been extensively studied, but EL of spoken language is still unexplored. We propose a conceptually simple and highly effective two-stage approach to tackle this issue. The first stage retrieves candidates with a dual encoder, which independently encodes mention context and entity descriptions. Each candidate is then reranked by a LUKE-based cross-encoder, which concatenates the mention and entity description. Different from previous cross-encoder which takes only words as input, our model adds entities into input. Experiments demonstrate that our model does not need large-scale training on Wikipedia corpus, and outperforms all previous models with or without Wikipedia training. Our approach ranks the \(1^\textrm{st}\) in NLPCC 2022 Shared Task on Speech EL Track 2 (Entity Disambiguation-Only).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The Wikidata page for the entity “George W. Bush”: https://www.wikidata.org/wiki/Q207.
- 2.
We use KILT’s processed Wikipedia dump, available at http://dl.fbaipublicfiles.com/KILT/kilt_knowledgesource.json.
- 3.
The training set and validation set of Wikipedia hyperlinks can be found at https://github.com/facebookresearch/KILT.
- 4.
For the number of candidates, according to Wu et al. [26], \(K=10\) is optimal, and increasing K to 100 gives minimal improvement but \(10\times \) run-time in reranking. Therefore we choose \(K=10\) finally.
- 5.
BLINK checkpoints can be downloaded at https://github.com/facebookresearch/BLINK/blob/main/download_blink_models.sh.
- 6.
We use alias table from GENRE [7] repository: https://dl.fbaipublicfiles.com/GENRE/mention2wikidataID_with_titles_label_alias_redirect.pkl.
- 7.
References
Barba, E., Procopio, L., Navigli, R.: ExtEnD: extractive entity disambiguation. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Dublin, Ireland, pp. 2478–2488. Association for Computational Linguistics, May 2022
Beltagy, I., Peters, M.E., Cohan, A.: Longformer: the long-document transformer. arXiv:2004.05150 (2020)
Benton, A., Dredze, M.: Entity linking for spoken language. In: Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Denver, Colorado, pp. 225–230. Association for Computational Linguistics, May–June 2015
Botha, J.A., Shan, Z., Gillick, D.: Entity linking in 100 languages. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 7833–7845. Association for Computational Linguistics, November 2020. https://aclanthology.org/2020.emnlp-main.630
De Cao, N., Aziz, W., Titov, I.: Question answering by reasoning across documents with graph convolutional networks. 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), Minneapolis, Minnesota, pp. 2306–2317. Association for Computational Linguistics, June 2019
De Cao, N., Aziz, W., Titov, I.: Highly parallel autoregressive entity linking with discriminative correction. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, Punta Cana, Dominican Republic, pp. 7662–7669. Association for Computational Linguistics, November 2021. https://aclanthology.org/2021.emnlp-main.604
De Cao, N., Izacard, G., Riedel, S., Petroni, F.: Autoregressive entity retrieval. In: International Conference on Learning Representations (2021). https://openreview.net/forum?id=5k8F6UU39V
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. 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), Minneapolis, Minnesota, pp. 4171–4186. Association for Computational Linguistics, June 2019. https://aclanthology.org/N19-1423
Gillick, D., et al.: Learning dense representations for entity retrieval. In: Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL), Hong Kong, China, pp. 528–537. Association for Computational Linguistics, November 2019. https://doi.org/10.18653/v1/K19-1049. https://aclanthology.org/K19-1049
Hernandez, F., Nguyen, V., Ghannay, S., Tomashenko, N., Estève, Y.: TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptation. In: Karpov, A., Jokisch, O., Potapova, R. (eds.) SPECOM 2018. LNCS (LNAI), vol. 11096, pp. 198–208. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-99579-3_21
Humeau, S., Shuster, K., Lachaux, M.A., Weston, J.: Poly-encoders: architectures and pre-training strategies for fast and accurate multi-sentence scoring. In: ICLR (2020)
Ji, H., Grishman, R.: Knowledge base population: successful approaches and challenges. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Portland, Oregon, USA, pp. 1148–1158. Association for Computational Linguistics, June 2011
Ji, H., Nothman, J., Hachey, B., et al.: Overview of tac-kbp2014 entity discovery and linking tasks. In: Proceedings of the Text Analysis Conference (TAC2014), pp. 1333–1339 (2014)
Johnson, J., Douze, M., Jégou, H.: Billion-scale similarity search with GPUs. IEEE Trans. Big Data 7(3), 535–547 (2019)
Joko, H., Hasibi, F., Balog, K., de Vries, A.P.: Conversational entity linking: problem definition and datasets. In: Proceedings of the 44rd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2021. ACM (2021)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7–9, 2015, Conference Track Proceedings (2015). http://arxiv.org/abs/1412.6980
Lewis, M., et al.: BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 7871–7880. Association for Computational Linguistics, July 2020. https://aclanthology.org/2020.acl-main.703
Lin, Y., Shen, S., Liu, Z., Luan, H., Sun, M.: Neural relation extraction with selective attention over instances. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Berlin, Germany, pp. 2124–2133. Association for Computational Linguistics, August 2016
Liu, X., Li, Y., Wu, H., Zhou, M., Wei, F., Lu, Y.: Entity linking for tweets. In: Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Sofia, Bulgaria, pp. 1304–1311. Association for Computational Linguistics, August 2013. https://aclanthology.org/P13-1128
Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach (2019)
Logeswaran, L., Chang, M.W., Lee, K., Toutanova, K., Devlin, J., Lee, H.: Zero-shot entity linking by reading entity descriptions. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy, pp. 3449–3460. Association for Computational Linguistics, July 2019
Muralidharan, D., et al.: Noise robust named entity understanding for voice assistants. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Papers, pp. 196–204. Association for Computational Linguistics, June 2021. https://aclanthology.org/2021.naacl-industry.25
Petroni, F., et al.: KILT: a benchmark for knowledge intensive language tasks. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 2523–2544. Association for Computational Linguistics, June 2021
Sun, T., et al.: CoLAKE: contextualized language and knowledge embedding. In: Proceedings of the 28th International Conference on Computational Linguistics, Barcelona, Spain, pp. 3660–3670. International Committee on Computational Linguistics, December 2020. https://aclanthology.org/2020.coling-main.327
Vaswani, A., et al.: Attention is all you need. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol. 30. Curran Associates, Inc. (2017)
Wu, L., Petroni, F., Josifoski, M., Riedel, S., Zettlemoyer, L.: Scalable zero-shot entity linking with dense entity retrieval. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 6397–6407. Association for Computational Linguistics, November 2020
Yamada, I., Asai, A., Shindo, H., Takeda, H., Matsumoto, Y.: LUKE: deep contextualized entity representations with entity-aware self-attention. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 6442–6454. Association for Computational Linguistics, November 2020. https://aclanthology.org/2020.emnlp-main.523
Yamada, I., Washio, K., Shindo, H., Matsumoto, Y.: Global entity disambiguation with BERT. In: NAACL. Association for Computational Linguistics (2022)
Zhang, W., Stratos, K.: Understanding hard negatives in noise contrastive estimation. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 1090–1101. Association for Computational Linguistics, June 2021
Zhang, Z., Han, X., Liu, Z., Jiang, X., Sun, M., Liu, Q.: ERNIE: enhanced language representation with informative entities. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy, pp. 1441–1451. Association for Computational Linguistics, July 2019
Acknowledgements
We appreciate the insightful feedback from anonymous reviewers. This work is jointly supported by grants: National Science Foundation of China (No. 62006061), Strategic Emerging Industry Development Special Funds of Shenzhen (No. JCYJ20200109113441941), and Stable Support Program for Higher Education Institutions of Shenzhen (No. GXWD20201230155427003-20200824155011001).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Xu, Z., Chen, Y., Shi, S., Hu, B. (2022). Enhancing Entity Linking with Contextualized Entity Embeddings. In: Lu, W., Huang, S., Hong, Y., Zhou, X. (eds) Natural Language Processing and Chinese Computing. NLPCC 2022. Lecture Notes in Computer Science(), vol 13552. Springer, Cham. https://doi.org/10.1007/978-3-031-17189-5_19
Download citation
DOI: https://doi.org/10.1007/978-3-031-17189-5_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-17188-8
Online ISBN: 978-3-031-17189-5
eBook Packages: Computer ScienceComputer Science (R0)