Please use this identifier to cite or link to this item:
https://hdl.handle.net/10356/162082
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Li, Qi | en_US |
dc.contributor.author | Mao, Kezhi | en_US |
dc.contributor.author | Li, Pengfei | en_US |
dc.contributor.author | Xu, Yuecong | en_US |
dc.contributor.author | Lo, Edmond Yat Man | en_US |
dc.date.accessioned | 2022-10-04T01:57:50Z | - |
dc.date.available | 2022-10-04T01:57:50Z | - |
dc.date.issued | 2022 | - |
dc.identifier.citation | Li, Q., Mao, K., Li, P., Xu, Y. & Lo, E. Y. M. (2022). A novel end-to-end neural network for simultaneous filtering of task-unrelated named entities and fine-grained typing of task-related named entities. Expert Systems With Applications, 204, 117498-. https://dx.doi.org/10.1016/j.eswa.2022.117498 | en_US |
dc.identifier.issn | 0957-4174 | en_US |
dc.identifier.uri | https://hdl.handle.net/10356/162082 | - |
dc.description.abstract | Recently, one emerging problem in Named Entity Typing (NET) is the fine-grained classification of task-related entities co-existing with task-unrelated entities. The traditional pipeline framework decomposes this problem into two sub-tasks. The first sub-task filters out the task-unrelated entities, while the second sub-task performs fine-grained classification for task-related entities. In the present study, we have developed an end-to-end neural network to solve the two sub-tasks simultaneously. The new model has two main merits. First, Mention–Mention (MM) relationship learning is developed to capture the interaction of task related and unrelated entities for producing more discriminative features. Second, an Improved Radial Basis Function classifier (ImRBF) with a novel training scheme is developed to jointly solve task-unrelated entity filtering and fine-grained classification of task-related entities. Experiments show that our model outperforms the pipeline methods by 3.3%–6% (F1 score) on the first sub-task and 1.8%–6.3% (F1 score) on the second sub-task. | en_US |
dc.language.iso | en | en_US |
dc.relation.ispartof | Expert Systems with Applications | en_US |
dc.rights | © 2022 Published by Elsevier Ltd. All rights reserved. | en_US |
dc.subject | Engineering::Electrical and electronic engineering | en_US |
dc.title | A novel end-to-end neural network for simultaneous filtering of task-unrelated named entities and fine-grained typing of task-related named entities | en_US |
dc.type | Journal Article | en |
dc.contributor.school | School of Electrical and Electronic Engineering | en_US |
dc.contributor.school | Interdisciplinary Graduate School (IGS) | en_US |
dc.contributor.research | Institute of Catastrophe Risk Management | en_US |
dc.identifier.doi | 10.1016/j.eswa.2022.117498 | - |
dc.identifier.scopus | 2-s2.0-85130627192 | - |
dc.identifier.volume | 204 | en_US |
dc.identifier.spage | 117498 | en_US |
dc.subject.keywords | Named Entity Typing | en_US |
dc.subject.keywords | Fine-Grained | en_US |
item.grantfulltext | none | - |
item.fulltext | No Fulltext | - |
Appears in Collections: | EEE Journal Articles IGS Journal Articles |
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.