A derivational model of discontinuous parsing

Mark Jan Nederhof; Anssi Yli-Jyra

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

A derivational model of discontinuous parsing

Mark Jan Nederhof, Anssi Yli-Jyra

School of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

19 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 language	English
Title of host publication	Language and Automata Theory and Applications
Subtitle of host publication	11th International Conference, LATA 2017, Umeå, Sweden, March 6-9, 2017, Proceedings
Editors	Frank Drewes, Carlos Martin-Vide, Bianca Truthe
Place of Publication	Cham
Publisher	Springer
Pages	299-310
DOIs	https://doi.org/10.1007/978-3-319-53733-7_22
Publication status	Published - 2017
Event	11th International Conference on Language and Automata Theory and Applications - Umeå, Sweden Duration: 6 Mar 2017 → 9 Mar 2017 Conference number: 11 http://grammars.grlmc.com/LATA2017/

Publication series

Name	Lecture Notes in Computer Science (Theoretical Computer Science and General Issues)
Publisher	Springer
Volume	10168
ISSN (Print)	0302-9743

Conference

Conference	11th International Conference on Language and Automata Theory and Applications
Abbreviated title	LATA 2017
Country/Territory	Sweden
City	Umeå
Period	6/03/17 → 9/03/17
Internet address	http://grammars.grlmc.com/LATA2017/

Keywords

Parsing
Grammars
Weighted automata

Access to Document

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

Nederhof_Derivational_LATA2017_AAM
© 2017, Springer International Publishing AG. This work has been made available online in accordance with the publisher’s policies. This is the author created, accepted version manuscript following peer review and may differ slightly from the final published version. The final published version of this work is available at link.springer.com / https://doi.org/10.1007/978-3-319-53733-7_22
Accepted author manuscript, 295 KB

Cite this

Nederhof, M. J., & Yli-Jyra, A. (2017). A derivational model of discontinuous parsing. In F. Drewes, C. Martin-Vide, & B. Truthe (Eds.), Language and Automata Theory and Applications: 11th International Conference, LATA 2017, Umeå, Sweden, March 6-9, 2017, Proceedings (pp. 299-310). (Lecture Notes in Computer Science (Theoretical Computer Science and General Issues); Vol. 10168). Springer. https://doi.org/10.1007/978-3-319-53733-7_22

Nederhof, Mark Jan ; Yli-Jyra, Anssi. / A derivational model of discontinuous parsing. Language and Automata Theory and Applications: 11th International Conference, LATA 2017, Umeå, Sweden, March 6-9, 2017, Proceedings. editor / Frank Drewes ; Carlos Martin-Vide ; Bianca Truthe. Cham : Springer, 2017. pp. 299-310 (Lecture Notes in Computer Science (Theoretical Computer Science and General Issues)).

@inproceedings{6479a3593a8d402bbe00eac1813ada83,

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 = "Parsing, Grammars, Weighted automata",

author = "Nederhof, {Mark Jan} and Anssi Yli-Jyra",

year = "2017",

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

language = "English",

series = "Lecture Notes in Computer Science (Theoretical Computer Science and General Issues)",

publisher = "Springer",

pages = "299--310",

editor = "Drewes, {Frank } and Carlos Martin-Vide and Bianca Truthe",

booktitle = "Language and Automata Theory and Applications",

address = "Netherlands",

note = "11th International Conference on Language and Automata Theory and Applications, LATA 2017 ; Conference date: 06-03-2017 Through 09-03-2017",

url = "http://grammars.grlmc.com/LATA2017/",

}

Nederhof, MJ & Yli-Jyra, A 2017, A derivational model of discontinuous parsing. in F Drewes, C Martin-Vide & B Truthe (eds), Language and Automata Theory and Applications: 11th International Conference, LATA 2017, Umeå, Sweden, March 6-9, 2017, Proceedings. Lecture Notes in Computer Science (Theoretical Computer Science and General Issues), vol. 10168, Springer, Cham, pp. 299-310, 11th International Conference on Language and Automata Theory and Applications, Umeå, Sweden, 6/03/17. https://doi.org/10.1007/978-3-319-53733-7_22

A derivational model of discontinuous parsing. / Nederhof, Mark Jan; Yli-Jyra, Anssi.
Language and Automata Theory and Applications: 11th International Conference, LATA 2017, Umeå, Sweden, March 6-9, 2017, Proceedings. ed. / Frank Drewes; Carlos Martin-Vide; Bianca Truthe. Cham: Springer, 2017. p. 299-310 (Lecture Notes in Computer Science (Theoretical Computer Science and General Issues); Vol. 10168).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - A derivational model of discontinuous parsing

AU - Nederhof, Mark Jan

AU - Yli-Jyra, Anssi

N1 - Conference code: 11

PY - 2017

Y1 - 2017

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 - Parsing

KW - Grammars

KW - Weighted automata

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

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

M3 - Conference contribution

T3 - Lecture Notes in Computer Science (Theoretical Computer Science and General Issues)

SP - 299

EP - 310

BT - Language and Automata Theory and Applications

A2 - Drewes, Frank

A2 - Martin-Vide, Carlos

A2 - Truthe, Bianca

PB - Springer

CY - Cham

T2 - 11th International Conference on Language and Automata Theory and Applications

Y2 - 6 March 2017 through 9 March 2017

ER -

Nederhof MJ, Yli-Jyra A. A derivational model of discontinuous parsing. In Drewes F, Martin-Vide C, Truthe B, editors, Language and Automata Theory and Applications: 11th International Conference, LATA 2017, Umeå, Sweden, March 6-9, 2017, Proceedings. Cham: Springer. 2017. p. 299-310. (Lecture Notes in Computer Science (Theoretical Computer Science and General Issues)). Epub 2017 Feb 16. doi: 10.1007/978-3-319-53733-7_22

A derivational model of discontinuous parsing

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this