Abstract | ||
---|---|---|
Fine-Grained entity typing is complicated by the fact that type labels form a hierarchical structure, and those training examples usually contain noisy type labels. This paper addresses these two issues by proposing a novel framework that simultaneously models the correlation among hierarchical types and the noise within the training data. Additionally, the framework contains an innovative training approach during which the noise in the training data is progressively removed. Experiments on standard benchmarking datasets validate the proposed framework and establish it as a new state of the art for this problem. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/TASLP.2022.3155281 | IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING |
Keywords | DocType | Volume |
Noise measurement, Training, Field effect transistors, Predictive models, Training data, Task analysis, Organizations, Entity typing, fine-grained entity typing, iterative training, label noise detection | Journal | 30 |
Issue | ISSN | Citations |
1 | 2329-9290 | 0 |
PageRank | References | Authors |
0.34 | 0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Junshuang Wu | 1 | 0 | 2.03 |
Richong Zhang | 2 | 232 | 39.67 |
Yongyi Mao | 3 | 524 | 61.02 |
Jinpeng Huai | 4 | 0 | 0.34 |