Coherent Entity Disambiguation via Modeling Topic and Categorical Dependency

Zilin Xiao, Linjun Shou, Xingyao Zhang, Jie Wu, Ming Gong, Daxin Jiang


Abstract
Previous entity disambiguation (ED) methods adopt a discriminative paradigm, where prediction is made based on matching scores between mention context and candidate entities using length-limited encoders. However, these methods often struggle to capture explicit discourse-level dependencies, resulting in incoherent predictions at the abstract level (e.g. topic or category). We propose CoherentED, an ED system equipped with novel designs aimed at enhancing the coherence of entity predictions. Our method first introduces an unsupervised variational autoencoder (VAE) to extract latent topic vectors of context sentences. This approach not only allows the encoder to handle longer documents more effectively, conserves valuable input space, but also keeps a topic-level coherence. Additionally, we incorporate an external category memory, enabling the system to retrieve relevant categories for undecided mentions. By employing step-by-step entity decisions, this design facilitates the modeling of entity-entity interactions, thereby maintaining maximum coherence at the category level. We achieve new state-of-the-art results on popular ED benchmarks, with an average improvement of 1.3 F1 points. Our model demonstrates particularly outstanding performance on challenging long-text scenarios.
Anthology ID:
2023.findings-emnlp.502
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7480–7492
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.502
DOI:
10.18653/v1/2023.findings-emnlp.502
Bibkey:
Cite (ACL):
Zilin Xiao, Linjun Shou, Xingyao Zhang, Jie Wu, Ming Gong, and Daxin Jiang. 2023. Coherent Entity Disambiguation via Modeling Topic and Categorical Dependency. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 7480–7492, Singapore. Association for Computational Linguistics.
Cite (Informal):
Coherent Entity Disambiguation via Modeling Topic and Categorical Dependency (Xiao et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-emnlp.502.pdf