Recursive non-autoregressive graph-to-graph transformer for dependency parsing with iterative refinement
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F21%3A10439968" target="_blank" >RIV/00216208:11320/21:10439968 - isvavai.cz</a>
Result on the web
<a href="https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=2tD1Qqsysf" target="_blank" >https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=2tD1Qqsysf</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1162/tacl_a_00358" target="_blank" >10.1162/tacl_a_00358</a>
Alternative languages
Result language
angličtina
Original language name
Recursive non-autoregressive graph-to-graph transformer for dependency parsing with iterative refinement
Original language description
We propose the Recursive Non-autoregressive Graph-to-Graph Transformer architecture (RNGTr) for the iterative refinement of arbitrary graphs through the recursive application of a non-autoregressive Graph-to-Graph Transformer and apply it to syntactic dependency parsing. We demonstrate the power and effectiveness of RNGTr on several dependency corpora, using a refinement model pre-trained with BERT. We also introduce Syntactic Transformer (SynTr), a non-recursive parser similar to our refinement model. RNGTr can improve the accuracy of a variety of initial parsers on 13 languages from the Universal Dependencies Treebanks, English and Chinese Penn Treebanks, and the German CoNLL2009 corpus, even improving over the new state-of-the-art results achieved by SynTr, significantly improving the state-of-the-art for all corpora tested.
Czech name
—
Czech description
—
Classification
Type
J<sub>SC</sub> - Article in a specialist periodical, which is included in the SCOPUS database
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
—
Others
Publication year
2021
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
Transactions of the Association for Computational Linguistics
ISSN
2307-387X
e-ISSN
—
Volume of the periodical
9
Issue of the periodical within the volume
01.02.2021
Country of publishing house
US - UNITED STATES
Number of pages
19
Pages from-to
120-138
UT code for WoS article
—
EID of the result in the Scopus database
2-s2.0-85110472390