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

Creating an essay based on a few given topics is a challenging NLP task.Although several effective methods for this problem, topic-to-essay generation,have appeared recently, there is still much room for improvement, especially interms of the coverage of the given topics and the coherence of the generatedtext. In this paper, we propose a novel approach called TegFormer whichutilizes the Transformer architecture where the encoder is enriched withdomain-specific contexts while the decoder is enhanced by a large-scalepre-trained language model. Specifically, a \emph{Topic-Extension} layercapturing the interaction between the given topics and their domain-specificcontexts is plugged into the encoder. Since the given topics are usuallyconcise and sparse, such an additional layer can bring more topic-relatedsemantics in to facilitate the subsequent natural language generation.Moreover, an \emph{Embedding-Fusion} module that combines the domain-specificword embeddings learnt from the given corpus and the general-purpose wordembeddings provided by a GPT-2 model pre-trained on massive text data isintegrated into the decoder. Since GPT-2 is at a much larger scale, it containsa lot more implicit linguistic knowledge which would help the decoder toproduce more grammatical and readable text. Extensive experiments have shownthat the pieces of text generated by TegFormer have better topic coverage andhigher text coherence than those from SOTA topic-to-essay techniques, accordingto automatic and human evaluations. As revealed by ablation studies, both theTopic-Extension layer and the Embedding-Fusion module contribute substantiallyto TegFormer's performance advantage.

TegFormer: Topic-to-Essay Generation with Good Topic Coverage and High Text Coherence