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

This work explores the intrinsic limitations of the popular one-hot encodingmethod in classification of intents when detection of out-of-scope (OOS) inputsis required. Although recent work has shown that there can be significantimprovements in OOS detection when the intent classes are represented asdense-vectors based on domain specific knowledge, we argue in this paper thatsuch gains are more likely due to advantages of dense-vector to one-hotencoding methods in representing the complexity of the OOS space. We start byshowing how dense-vector encodings can create OOS spaces with much richertopologies than one-hot encoding methods. We then demonstrate empirically,using four standard intent classification datasets, that knowledge-free,randomly generated dense-vector encodings of intent classes can yield massive,over 20% gains over one-hot encodings, and also outperform the previous, domainknowledge-based, SOTA of one of the datasets. We finish by describing a novelalgorithm to search for good dense-vector encodings and present initial butpromising experimental results of its use.

Exploring the Advantages of Dense-Vector to One-Hot Encoding of Intent Classes in Out-of-Scope Detection Tasks