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

Many NLP tasks require to automatically identify the most significant wordsin a text. In this work, we derive word significance from models trained tosolve semantic task: Natural Language Inference and Paraphrase Identification.Using an attribution method aimed to explain the predictions of these models,we derive importance scores for each input token. We evaluate their relevanceusing a so-called cross-task evaluation: Analyzing the performance of one modelon an input masked according to the other model's weight, we show that ourmethod is robust with respect to the choice of the initial task. Additionally,we investigate the scores from the syntax point of view and observe interestingpatterns, e.g. words closer to the root of a syntactic tree receive higherimportance scores. Altogether, these observations suggest that our method canbe used to identify important words in sentences without any explicit wordimportance labeling in training.

Assessing Word Importance Using Models Trained for Semantic Tasks