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

The rise of pre-trained language models has yielded substantial progress inthe vast majority of Natural Language Processing (NLP) tasks. However, ageneric approach towards the pre-training procedure can naturally besub-optimal in some cases. Particularly, fine-tuning a pre-trained languagemodel on a source domain and then applying it to a different target domain,results in a sharp performance decline of the eventual classifier for manysource-target domain pairs. Moreover, in some NLP tasks, the output categoriessubstantially differ between domains, making adaptation even more challenging.This, for example, happens in the task of aspect extraction, where the aspectsof interest of reviews of, e.g., restaurants or electronic devices may be verydifferent. This paper presents a new fine-tuning scheme for BERT, which aims toaddress the above challenges. We name this scheme DILBERT: Domain InvariantLearning with BERT, and customize it for aspect extraction in the unsuperviseddomain adaptation setting. DILBERT harnesses the categorical information ofboth the source and the target domains to guide the pre-training processtowards a more domain and category invariant representation, thus closing thegap between the domains. We show that DILBERT yields substantial improvementsover state-of-the-art baselines while using a fraction of the unlabeled data,particularly in more challenging domain adaptation setups.

DILBERT: Customized Pre-Training for Domain Adaptation withCategory Shift, with an Application to Aspect Extraction