HPSG-Inspired Joint Neural Constituent and Dependency Parsing in O(n(3)) Time Complexity

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F22%3A10441614" target="_blank" >RIV/00216208:11320/22:10441614 - isvavai.cz</a>

Result on the web

<a href="https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=rQMY.bNWG9" target="_blank" >https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=rQMY.bNWG9</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/TASLP.2021.3138715" target="_blank" >10.1109/TASLP.2021.3138715</a>

Result language

angličtina

Original language name

HPSG-Inspired Joint Neural Constituent and Dependency Parsing in O(n(3)) Time Complexity

Original language description

Constituent and dependency parsing, the two classic forms of syntactic parsing, have been found to benefit from joint training and decoding under a uniform formalism, inspired by Head-driven Phrase Structure Grammar (HPSG). We thus refer to this joint parsing of constituency and dependency as HPSG-like parsing. However, in HPSG-like parsing, decoding this unified grammar has a higher time complexity (O(n(3))) than decoding either form individually (O(n(3))) since more factors have to be considered during decoding. We thus propose an improved head scorer that helps achieve a novel performance-preserved parser in O(n(3)) time complexity. Furthermore, on the basis of this proposed practical HPSG-like parser, we investigated the strengths of HPSG-like parsing and explored the general method of training an HPSG-like parser from only a constituent or dependency annotations in a multilingual scenario. We thus present a more effective, more in-depth, and general work on HPSG-like parsing.

Czech name

—

Czech description

—

Type

J_imp - Article in a specialist periodical, which is included in the Web of Science database

CEP classification

—

OECD FORD branch

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

Project

—

Continuities

—

Publication year

2022

Confidentiality

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

Name of the periodical

IEEE - ACM Transactions on Audio, Speech, and Language Processing

ISSN

2329-9290

e-ISSN

2329-9304

Volume of the periodical

30

Issue of the periodical within the volume

28.12.2021

Country of publishing house

US - UNITED STATES

Number of pages

12

Pages from-to

355-366

UT code for WoS article

000742717400001

EID of the result in the Scopus database

2-s2.0-85122302994