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

Extreme multi-label text classification (XMTC) is the task of finding themost relevant subset labels from an extremely large-scale label collection.Recently, some deep learning models have achieved state-of-the-art results inXMTC tasks. These models commonly predict scores for all labels by a fullyconnected layer as the last layer of the model. However, such models can'tpredict a relatively complete and variable-length label subset for eachdocument, because they select positive labels relevant to the document by afixed threshold or take top k labels in descending order of scores. A lesspopular type of deep learning models called sequence-to-sequence (Seq2Seq)focus on predicting variable-length positive labels in sequence style. However,the labels in XMTC tasks are essentially an unordered set rather than anordered sequence, the default order of labels restrains Seq2Seq models intraining. To address this limitation in Seq2Seq, we propose an autoregressivesequence-to-set model for XMTC tasks named OTSeq2Set. Our model generatespredictions in student-forcing scheme and is trained by a loss function basedon bipartite matching which enables permutation-invariance. Meanwhile, we usethe optimal transport distance as a measurement to force the model to focus onthe closest labels in semantic label space. Experiments show that OTSeq2Setoutperforms other competitive baselines on 4 benchmark datasets. Especially, onthe Wikipedia dataset with 31k labels, it outperforms the state-of-the-artSeq2Seq method by 16.34% in micro-F1 score. The code is available athttps://github.com/caojie54/OTSeq2Set.

OTSeq2Set: An Optimal Transport Enhanced Sequence-to-Set Model for Extreme Multi-label Text Classification