Recursive non-autoregressive graph-to-graph transformer for dependency parsing with iterative refinement

Kód výsledku v 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>

Výsledek na webu

<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>

Jazyk výsledku

angličtina

Název v původním jazyce

Recursive non-autoregressive graph-to-graph transformer for dependency parsing with iterative refinement

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

Recursive non-autoregressive graph-to-graph transformer for dependency parsing with iterative refinement

Popis výsledku anglicky

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.

Druh

J_SC - Článek v periodiku v databázi SCOPUS

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

—

Rok uplatnění

2021

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Transactions of the Association for Computational Linguistics

ISSN

2307-387X

e-ISSN

—

Svazek periodika

9

Číslo periodika v rámci svazku

01.02.2021

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

19

Strana od-do

120-138

Kód UT WoS článku

—

EID výsledku v databázi Scopus

2-s2.0-85110472390