A Joint Learning Framework for the CCKS-2020 Financial Event Extraction Task | Zendy

Jiawei Sheng | Zendy; Qian Li | Zendy; Yiming Hei | Zendy; Shu Guo | Zendy; Bowen Yu | Zendy; Lihong Wang | Zendy; Min He | Zendy; Tingwen Liu | Zendy; Hongbo Xu | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

A Joint Learning Framework for the CCKS-2020 Financial Event Extraction Task

Author(s) -

Jiawei Sheng,

Qian Li,

Yiming Hei,

Shu Guo,

Bowen Yu,

Lihong Wang,

Min He,

Tingwen Liu,

Hongbo Xu

Publication year - 2021

Publication title -

data intelligence

Language(s) - English

Resource type - Journals

eISSN - 2096-7004

pISSN - 2641-435X

DOI - 10.1162/dint_a_00098

Subject(s) - computer science , task (project management) , event (particle physics) , normalization (sociology) , joint (building) , artificial intelligence , multi task learning , focus (optics) , machine learning , engineering , architectural engineering , physics , systems engineering , optics , quantum mechanics , sociology , anthropology

This paper presents a winning solution for the CCKS-2020 financial event extraction task, where the goal is to identify event types, triggers and arguments in sentences across multiple event types. In this task, we focus on resolving two challenging problems (i.e., low resources and element overlapping) by proposing a joint learning framework, named SaltyFishes. We first formulate the event extraction task as a joint probability model. By sharing parameters in the model across different types, we can learn to adapt to low-resource events based on high-resource events. We further address the element overlapping problems by a mechanism of Conditional Layer Normalization, achieving even better extraction accuracy. The overall approach achieves an F1-score of 87.8% which ranks the first place in the competition.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research