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

In the literature, the research on abstract meaning representation (AMR)parsing is much restricted by the size of human-curated dataset which iscritical to build an AMR parser with good performance. To alleviate such datasize restriction, pre-trained models have been drawing more and more attentionin AMR parsing. However, previous pre-trained models, like BERT, areimplemented for general purpose which may not work as expected for the specifictask of AMR parsing. In this paper, we focus on sequence-to-sequence (seq2seq)AMR parsing and propose a seq2seq pre-training approach to build pre-trainedmodels in both single and joint way on three relevant tasks, i.e., machinetranslation, syntactic parsing, and AMR parsing itself. Moreover, we extend thevanilla fine-tuning method to a multi-task learning fine-tuning method thatoptimizes for the performance of AMR parsing while endeavors to preserve theresponse of pre-trained models. Extensive experimental results on two Englishbenchmark datasets show that both the single and joint pre-trained modelssignificantly improve the performance (e.g., from 71.5 to 80.2 on AMR 2.0),which reaches the state of the art. The result is very encouraging since weachieve this with seq2seq models rather than complex models. We make our codeand model available at https://github.com/xdqkid/S2S-AMR-Parser.

Improving AMR Parsing with Sequence-to-Sequence Pre-training