Aligning Packed Dependency Trees: A Theory of Composition for Distributional Semantics

David Weir; Julie Weeds; Jeremy Reffin; Thomas Kober

doi:10.1162/COLI_a_00265

Aligning Packed Dependency Trees: A Theory of Composition for Distributional Semantics

David Weir, Julie Weeds, Jeremy Reffin, Thomas Kober

Research output: Contribution to journal › Article › peer-review

Abstract / Description of output

We present a new framework for compositional distributional semantics in which the distributional contexts of lexemes are expressed in terms of anchored packed dependency trees. We show that these structures have the potential to capture the full sentential contexts of a lexeme and provide a uniform basis for the composition of distributional knowledge in a way that captures both mutual disambiguation and generalization.

Original language	English
Pages (from-to)	727-761
Number of pages	35
Journal	Computational Linguistics
Volume	42
Issue number	4
Early online date	1 Dec 2016
DOIs	https://doi.org/10.1162/COLI_a_00265
Publication status	Published - 26 Jan 2017

Access to Document

10.1162/COLI_a_00265

Aligning Packed Dependency TreesAccepted author manuscript, 823 KBLicence: Creative Commons: Attribution (CC-BY)

https://www.mitpressjournals.org/doi/pdf/10.1162/COLI_a_00265

Cite this

@article{1483b269641b4944a9cef34b8c5f4779,

title = "Aligning Packed Dependency Trees: A Theory of Composition for Distributional Semantics",

abstract = "We present a new framework for compositional distributional semantics in which the distributional contexts of lexemes are expressed in terms of anchored packed dependency trees. We show that these structures have the potential to capture the full sentential contexts of a lexeme and provide a uniform basis for the composition of distributional knowledge in a way that captures both mutual disambiguation and generalization.",

author = "David Weir and Julie Weeds and Jeremy Reffin and Thomas Kober",

year = "2017",

month = jan,

day = "26",

doi = "10.1162/COLI_a_00265",

language = "English",

volume = "42",

pages = "727--761",

journal = "Computational Linguistics",

issn = "0891-2017",

publisher = "MIT Press Journals",

number = "4",

}

TY - JOUR

T1 - Aligning Packed Dependency Trees: A Theory of Composition for Distributional Semantics

AU - Weir, David

AU - Weeds, Julie

AU - Reffin, Jeremy

AU - Kober, Thomas

PY - 2017/1/26

Y1 - 2017/1/26

N2 - We present a new framework for compositional distributional semantics in which the distributional contexts of lexemes are expressed in terms of anchored packed dependency trees. We show that these structures have the potential to capture the full sentential contexts of a lexeme and provide a uniform basis for the composition of distributional knowledge in a way that captures both mutual disambiguation and generalization.

AB - We present a new framework for compositional distributional semantics in which the distributional contexts of lexemes are expressed in terms of anchored packed dependency trees. We show that these structures have the potential to capture the full sentential contexts of a lexeme and provide a uniform basis for the composition of distributional knowledge in a way that captures both mutual disambiguation and generalization.

U2 - 10.1162/COLI_a_00265

DO - 10.1162/COLI_a_00265

M3 - Article

SN - 0891-2017

VL - 42

SP - 727

EP - 761

JO - Computational Linguistics

JF - Computational Linguistics

IS - 4

ER -

Aligning Packed Dependency Trees: A Theory of Composition for Distributional Semantics

Abstract / Description of output

Access to Document

Fingerprint

Cite this