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

Dialogue State Tracking (DST) models often employ intricate neural networkarchitectures, necessitating substantial training data, and their inferenceprocesses lack transparency. This paper proposes a method that extractslinguistic knowledge via an unsupervised framework and subsequently utilizesthis knowledge to augment BERT's performance and interpretability in DST tasks.The knowledge extraction procedure is computationally economical and does notnecessitate annotations or additional training data. The injection of theextracted knowledge necessitates the addition of only simple neural modules. Weemploy the Convex Polytopic Model (CPM) as a feature extraction tool for DSTtasks and illustrate that the acquired features correlate with the syntacticand semantic patterns in the dialogues. This correlation facilitates acomprehensive understanding of the linguistic features influencing the DSTmodel's decision-making process. We benchmark this framework on various DSTtasks and observe a notable improvement in accuracy.

Injecting linguistic knowledge into BERT for Dialogue State Tracking