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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Natural Language Inference (NLI) models are known to learn from biases andartefacts within their training data, impacting how well they generalise toother unseen datasets. Existing de-biasing approaches focus on preventing themodels from learning these biases, which can result in restrictive models andlower performance. We instead investigate teaching the model how a human wouldapproach the NLI task, in order to learn features that will generalise betterto previously unseen examples. Using natural language explanations, wesupervise the model's attention weights to encourage more attention to be paidto the words present in the explanations, significantly improving modelperformance. Our experiments show that the in-distribution improvements of thismethod are also accompanied by out-of-distribution improvements, with thesupervised models learning from features that generalise better to other NLIdatasets. Analysis of the model indicates that human explanations encourageincreased attention on the important words, with more attention paid to wordsin the premise and less attention paid to punctuation and stop-words.

Supervising Model Attention with Human Explanations for Robust Natural Language Inference