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

We propose TANDA, an effective technique for fine-tuning pre-trainedTransformer models for natural language tasks. Specifically, we first transfera pre-trained model into a model for a general task by fine-tuning it with alarge and high-quality dataset. We then perform a second fine-tuning step toadapt the transferred model to the target domain. We demonstrate the benefitsof our approach for answer sentence selection, which is a well-known inferencetask in Question Answering. We built a large scale dataset to enable thetransfer step, exploiting the Natural Questions dataset. Our approachestablishes the state of the art on two well-known benchmarks, WikiQA andTREC-QA, achieving MAP scores of 92% and 94.3%, respectively, which largelyoutperform the previous highest scores of 83.4% and 87.5%, obtained in veryrecent work. We empirically show that TANDA generates more stable and robustmodels reducing the effort required for selecting optimal hyper-parameters.Additionally, we show that the transfer step of TANDA makes the adaptation stepmore robust to noise. This enables a more effective use of noisy datasets forfine-tuning. Finally, we also confirm the positive impact of TANDA in anindustrial setting, using domain specific datasets subject to different typesof noise.

TANDA: Transfer and Adapt Pre-Trained Transformer Models for Answer Sentence Selection