Download | - View final version: Modeling noisy hierarchical types in fine-grained entity typing: a content-based weighting approach (PDF, 352 KiB)
|
---|
DOI | Resolve DOI: https://doi.org/10.24963/ijcai.2019/731 |
---|
Author | Search for: Wu, Junshuang; Search for: Zhang, Richong; Search for: Mao, Yongyi; Search for: Guo, Hongyu1; Search for: Huai, Jinpeng |
---|
Affiliation | - National Research Council of Canada. Digital Technologies
|
---|
Format | Text, Article |
---|
Conference | IJCAI-2019 MACAO - Twenty-Eighth International Joint Conference on Artificial Intelligence, Aug. 10-16, 2019, Macao, China |
---|
Subject | natural language processing: information extraction; natural language processing: NLP applications and tools |
---|
Abstract | Fine-grained entity typing (FET), which annotates the entities in a sentence with a set of finely specified type labels, often serves as the first and critical step towards many natural language processing tasks. Despite great processes have been made, current FET methods have difficulty to cope with the noisy labels which naturally come with the data acquisition processes. Existing FET approaches either pre-process to clean the noise or simply focus on one of the noisy labels, sidestepping the fact that those noises are related and content dependent. In this paper, we directly model the structured, noisy labels with a novel content-sensitive weighting schema. Coupled with a newly devised cost function and a hierarchical type embedding strategy, our method leverages a random walk process to effectively weight out noisy labels during training. Experiments on several benchmark datasets validate the effectiveness of the proposed framework and establish it as a new state of the art strategy for noisy entity typing problem. |
---|
Publication date | 2019-08-16 |
---|
Publisher | International Joint Conferences on Artificial Intelligence Organization |
---|
In | |
---|
Language | English |
---|
Peer reviewed | Yes |
---|
Export citation | Export as RIS |
---|
Report a correction | Report a correction (opens in a new tab) |
---|
Record identifier | 1f63dcc1-fd5f-4f10-ae55-3e3c8d0338d5 |
---|
Record created | 2021-07-16 |
---|
Record modified | 2021-07-19 |
---|