English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Multi-task learning (MTL) aims at achieving a better model by leveraging dataand knowledge from multiple tasks. However, MTL does not always work --sometimes negative transfer occurs between tasks, especially when aggregatingloosely related skills, leaving it an open question when MTL works. Previousstudies show that MTL performance can be improved by algorithmic tricks.However, what tasks and skills should be included is less well explored. Inthis work, we conduct a case study in Financial NLP where multiple datasetsexist for skills relevant to the domain, such as numeric reasoning andsentiment analysis. Due to the task difficulty and data scarcity in theFinancial NLP domain, we explore when aggregating such diverse skills frommultiple datasets with MTL can work. Our findings suggest that the key to MTLsuccess lies in skill diversity, relatedness between tasks, and choice ofaggregation size and shared capacity. Specifically, MTL works well when tasksare diverse but related, and when the size of the task aggregation and theshared capacity of the model are balanced to avoid overwhelming certain tasks.

When Does Aggregating Multiple Skills with Multi-Task Learning Work? A Case Study in Financial NLP