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

Recent studies suggest that the existing neural models have difficultyhandling repeated items in sequential recommendation tasks. However, ourunderstanding of this difficulty is still limited. In this study, wesubstantially advance this field by identifying a major source of the problem:the single hidden state embedding and static item embeddings in the outputsoftmax layer. Specifically, the similarity structure of the global itemembeddings in the softmax layer sometimes forces the single hidden stateembedding to be close to new items when copying is a better choice, whilesometimes forcing the hidden state to be close to the items from the inputinappropriately. To alleviate the problem, we adapt the recently-proposedsoftmax alternatives such as softmax-CPR to sequential recommendation tasks anddemonstrate that the new softmax architectures unleash the capability of theneural encoder on learning when to copy and when to exclude the items from theinput sequence. By only making some simple modifications on the output softmaxlayer for SASRec and GRU4Rec, softmax-CPR achieves consistent improvement in 12datasets. With almost the same model size, our best method not only improvesthe average NDCG@10 of GRU4Rec in 5 datasets with duplicated items by 10%(4%-17% individually) but also improves 7 datasets without duplicated items by24% (8%-39%)!

To Copy, or not to Copy; That is a Critical Issue of the Output Softmax Layer in Neural Sequential Recommenders