A Derivational Model of Discontinuous Parsing

Mark-Jan Nederhof; Anssi Mikael Yli-Jyrä

doi:10.1007/978-3-319-53733-7_22

A Derivational Model of Discontinuous Parsing

Mark-Jan Nederhof, Anssi Mikael Yli-Jyrä

Språkteknologi

Forskningsoutput: Kapitel i bok/rapport/konferenshandling › Kapitel › Vetenskaplig › Peer review

Sammanfattning

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.

Bidragets översatta titel	Epäjatkuvan jäsennyspuun johtoon perustuva tilastollinen malli
Originalspråk	engelska
Titel på värdpublikation	Language and Automata Theory and Applications : LATA 2017
Redaktörer	Carlos Martín-Vide
Antal sidor	12
Utgivningsort	Berlin
Förlag	Springer-Verlag
Utgivningsdatum	6 mars 2017
Sidor	299-310
ISBN (tryckt)	978-3-319-53732-0
ISBN (elektroniskt)	978-3-319-53733-7
DOI	https://doi.org/10.1007/978-3-319-53733-7_22
Status	Publicerad - 6 mars 2017
MoE-publikationstyp	A3 Del av bok eller annan forskningsbok

Publikationsserier

Namn	Lecture Notes in Computer Science
Förlag	Springer
ISSN (tryckt)	0302-9743
ISSN (elektroniskt)	1611-3349

Vetenskapsgrenar

111 Matematik
113 Data- och informationsvetenskap
6121 Språkvetenskaper

Åtkomst av dokument

10.1007/978-3-319-53733-7_22Licens: !!Unspecified

Andra filer och länkar

Nederhof-Yli-Jyrä2017_Chapter_ADerivationalModelOfDiscontinu

1 Slutfört

ADEQSYNTAX: Käytettävä äärellistilainen malli adekvaatille kieliopilliselle kompleksisuudelle
Yli-Jyrä, A.
Suomen tietokirjailijat
01/09/2013 → 30/04/2019
Projekt: Forskningsprojekt

1 Akademiskt besök på HU

Edward Gibson
Anssi Yli-Jyrä (Värd)
28 nov. 2016 → 4 dec. 2016
Aktivitet: Typer för att vara värd för en besökare › Akademiskt besök på HU

Citera det här

@inbook{601967b67f9c46e9b8b077c46db8ba10,

title = "A Derivational Model of Discontinuous Parsing",

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.",

keywords = "111 Mathematics, derivaatio, grammars, perplexity, 113 Computer and information sciences, parsing, grammars, weighted automata, perplexity, derivations, Probabilistic model, weighted automata, context-free derivation, discontinuity, derivation, 6121 Languages, dependenssikielioppi, j{\"a}sent{\"a}minen, sanaj{\"a}rjestys, kielen kompleksisuus, parsing, syntactic structures",

author = "Mark-Jan Nederhof and Yli-Jyr{\"a}, {Anssi Mikael}",

year = "2017",

month = mar,

day = "6",

doi = "10.1007/978-3-319-53733-7_22",

language = "English",

isbn = "978-3-319-53732-0",

series = "Lecture Notes in Computer Science",

publisher = "Springer-Verlag",

pages = "299--310",

editor = "Carlos Mart{\'i}n-Vide",

booktitle = "Language and Automata Theory and Applications",

address = "Germany",

}

TY - CHAP

T1 - A Derivational Model of Discontinuous Parsing

AU - Nederhof, Mark-Jan

AU - Yli-Jyrä, Anssi Mikael

PY - 2017/3/6

Y1 - 2017/3/6

N2 - 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.

AB - 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.

KW - 111 Mathematics

KW - derivaatio

KW - grammars

KW - perplexity

KW - 113 Computer and information sciences

KW - parsing

KW - grammars

KW - weighted automata

KW - perplexity

KW - derivations

KW - Probabilistic model

KW - weighted automata

KW - context-free derivation

KW - discontinuity

KW - derivation

KW - 6121 Languages

KW - dependenssikielioppi

KW - jäsentäminen

KW - sanajärjestys

KW - kielen kompleksisuus

KW - parsing

KW - syntactic structures

U2 - 10.1007/978-3-319-53733-7_22

DO - 10.1007/978-3-319-53733-7_22

M3 - Chapter

SN - 978-3-319-53732-0

T3 - Lecture Notes in Computer Science

SP - 299

EP - 310

BT - Language and Automata Theory and Applications

A2 - Martín-Vide, Carlos

PB - Springer-Verlag

CY - Berlin

ER -

A Derivational Model of Discontinuous Parsing

Sammanfattning

Publikationsserier

Vetenskapsgrenar

Åtkomst av dokument

Andra filer och länkar

Projekt

ADEQSYNTAX: Käytettävä äärellistilainen malli adekvaatille kieliopilliselle kompleksisuudelle

Aktiviteter

Edward Gibson

Citera det här