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

A BERT-based Neural Ranking Model (NRM) can be either a crossencoder or abi-encoder. Between the two, bi-encoder is highly efficient because all thedocuments can be pre-processed before the actual query time. In this work, weshow two approaches for improving the performance of BERT-based bi-encoders.The first approach is to replace the full fine-tuning step with a lightweightfine-tuning. We examine lightweight fine-tuning methods that are adapter-based,prompt-based, and hybrid of the two. The second approach is to developsemi-Siamese models where queries and documents are handled with a limitedamount of difference. The limited difference is realized by learning twolightweight fine-tuning modules, where the main language model of BERT is keptcommon for both query and document. We provide extensive experiment results formonoBERT, TwinBERT, and ColBERT where three performance metrics are evaluatedover Robust04, ClueWeb09b, and MS-MARCO datasets. The results confirm that bothlightweight fine-tuning and semi-Siamese are considerably helpful for improvingBERT-based bi-encoders. In fact, lightweight fine-tuning is helpful forcrossencoder, too

Semi-Siamese Bi-encoder Neural Ranking Model Using Lightweight Fine-Tuning