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

Previous works have demonstrated the effectiveness of utilising pre-trainedsentence encoders based on their sentence representations for meaningcomparison tasks. Though such representations are shown to capture hiddensyntax structures, the direct similarity comparison between them exhibits weaksensitivity to word order and structural differences in given sentences. Asingle similarity score further makes the comparison process hard to interpret.Therefore, we here propose to combine sentence encoders with an alignmentcomponent by representing each sentence as a list of predicate-argument spans(where their span representations are derived from sentence encoders), anddecomposing the sentence-level meaning comparison into the alignment betweentheir spans for paraphrase identification tasks. Empirical results show thatthe alignment component brings in both improved performance andinterpretability for various sentence encoders. After closer investigation, theproposed approach indicates increased sensitivity to structural difference andenhanced ability to distinguish non-paraphrases with high lexical overlap.

Towards Structure-aware Paraphrase Identification with Phrase Alignment Using Sentence Encoders