A derivational model of discontinuous parsing

Mark Jan Nederhof, Anssi Yli-Jyra

Research output: Chapter in Book/Report/Conference proceedingConference contribution

12 Downloads (Pure)

Abstract

The notion of latent-variable probabilistic context-free derivation of syntactic structures is enhanced to allow heads and unrestricted discontinuities. The chosen formalization covers both constituent parsing and dependency parsing. The derivational model is accompanied by an equivalent probabilistic automaton model. By the new framework, one obtains a probability distribution over the space of all discontinuous parses. This lends itself to intrinsic evaluation in terms of perplexity, as shown in experiments.
Original languageEnglish
Title of host publicationLanguage and Automata Theory and Applications
Subtitle of host publication11th International Conference, LATA 2017, Umeå, Sweden, March 6-9, 2017, Proceedings
EditorsFrank Drewes, Carlos Martin-Vide, Bianca Truthe
Place of PublicationCham
PublisherSpringer
Pages299-310
DOIs
Publication statusPublished - 2017
Event11th International Conference on Language and Automata Theory and Applications - Umeå, Sweden
Duration: 6 Mar 20179 Mar 2017
Conference number: 11
http://grammars.grlmc.com/LATA2017/

Publication series

NameLecture Notes in Computer Science (Theoretical Computer Science and General Issues)
PublisherSpringer
Volume10168
ISSN (Print)0302-9743

Conference

Conference11th International Conference on Language and Automata Theory and Applications
Abbreviated titleLATA 2017
Country/TerritorySweden
CityUmeå
Period6/03/179/03/17
Internet address

Keywords

  • Parsing
  • Grammars
  • Weighted automata

Fingerprint

Dive into the research topics of 'A derivational model of discontinuous parsing'. Together they form a unique fingerprint.

Cite this