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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Emotion recognition in conversations (ERC) is a crucial task for buildinghuman-like conversational agents. While substantial efforts have been devotedto ERC for chit-chat dialogues, the task-oriented counterpart is largely leftunattended. Directly applying chit-chat ERC models to task-oriented dialogues(ToDs) results in suboptimal performance as these models overlook key featuressuch as the correlation between emotions and task completion in ToDs. In thispaper, we propose a framework that turns a chit-chat ERC model into atask-oriented one, addressing three critical aspects: data, features andobjective. First, we devise two ways of augmenting rare emotions to improve ERCperformance. Second, we use dialogue states as auxiliary features toincorporate key information from the goal of the user. Lastly, we leverage amulti-aspect emotion definition in ToDs to devise a multi-task learningobjective and a novel emotion-distance weighted loss function. Our frameworkyields significant improvements for a range of chit-chat ERC models on EmoWOZ,a large-scale dataset for user emotion in ToDs. We further investigate thegeneralisability of the best resulting model to predict user satisfaction indifferent ToD datasets. A comparison with supervised baselines shows a strongzero-shot capability, highlighting the potential usage of our framework inwider scenarios.

From Chatter to Matter: Addressing Critical Steps of Emotion Recognition Learning in Task-oriented Dialogue