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

This paper presents a self-supervised learning method for pointer-generatornetworks to improve spoken-text normalization. Spoken-text normalization thatconverts spoken-style text into style normalized text is becoming an importanttechnology for improving subsequent processing such as machine translation andsummarization. The most successful spoken-text normalization method to date issequence-to-sequence (seq2seq) mapping using pointer-generator networks thatpossess a copy mechanism from an input sequence. However, these models requirea large amount of paired data of spoken-style text and style normalized text,and it is difficult to prepare such a volume of data. In order to constructspoken-text normalization model from the limited paired data, we focus onself-supervised learning which can utilize unpaired text data to improveseq2seq models. Unfortunately, conventional self-supervised learning methods donot assume that pointer-generator networks are utilized. Therefore, we proposea novel self-supervised learning method, MAsked Pointer-Generator Network(MAPGN). The proposed method can effectively pre-train the pointer-generatornetwork by learning to fill masked tokens using the copy mechanism. Ourexperiments demonstrate that MAPGN is more effective for pointer-generatornetworks than the conventional self-supervised learning methods in twospoken-text normalization tasks.

MAPGN: MAsked Pointer-Generator Network for sequence-to-sequence pre-training