Unsupervised context sensitive language acquisition from large, untagged corpora

Zach Solan; Eytan Ruppin; David Horn; Shimon Edelman

Unsupervised context sensitive language acquisition from large, untagged corpora

Zach Solan^*, Eytan Ruppin, David Horn, Shimon Edelman

^*Corresponding author for this work

Research output: Contribution to conference › Paper › peer-review

1 Scopus citations

Abstract

An alternative hypothesis, according to which syntax is an abstraction that emerges from exposure to language, coexisting with the corpus data within the same representational mechanism is discussed. The Automatic Distillation of Structure (ADIOS) model is used which has two components which include a representational data structure, which is a directed multi graph, and a pattern acquisition (PA) algorithm that refines the graph in an unsupervised fashion. The ADIOS model incrementally learns the syntax of English from raw input by distilling structural regularities from the accrued statistical cooccurence and contextual cues. The patterns learned by ADIOS are also more powerful than context free rewriting rules, because of their conservative nature.

Original language	English
Pages	61-64
Number of pages	4
State	Published - 2004
Event	2004 AAAI Spring Symposium - Stanford, CA, United States Duration: 22 Mar 2004 → 24 Mar 2004

Conference

Conference	2004 AAAI Spring Symposium
Country/Territory	United States
City	Stanford, CA
Period	22/03/04 → 24/03/04

Cite this

@conference{2b46007ed65044b1b346964763a4b56c,

title = "Unsupervised context sensitive language acquisition from large, untagged corpora",

abstract = "An alternative hypothesis, according to which syntax is an abstraction that emerges from exposure to language, coexisting with the corpus data within the same representational mechanism is discussed. The Automatic Distillation of Structure (ADIOS) model is used which has two components which include a representational data structure, which is a directed multi graph, and a pattern acquisition (PA) algorithm that refines the graph in an unsupervised fashion. The ADIOS model incrementally learns the syntax of English from raw input by distilling structural regularities from the accrued statistical cooccurence and contextual cues. The patterns learned by ADIOS are also more powerful than context free rewriting rules, because of their conservative nature.",

author = "Zach Solan and Eytan Ruppin and David Horn and Shimon Edelman",

year = "2004",

language = "אנגלית",

pages = "61--64",

note = "2004 AAAI Spring Symposium ; Conference date: 22-03-2004 Through 24-03-2004",

}

TY - CONF

T1 - Unsupervised context sensitive language acquisition from large, untagged corpora

AU - Solan, Zach

AU - Ruppin, Eytan

AU - Horn, David

AU - Edelman, Shimon

PY - 2004

Y1 - 2004

N2 - An alternative hypothesis, according to which syntax is an abstraction that emerges from exposure to language, coexisting with the corpus data within the same representational mechanism is discussed. The Automatic Distillation of Structure (ADIOS) model is used which has two components which include a representational data structure, which is a directed multi graph, and a pattern acquisition (PA) algorithm that refines the graph in an unsupervised fashion. The ADIOS model incrementally learns the syntax of English from raw input by distilling structural regularities from the accrued statistical cooccurence and contextual cues. The patterns learned by ADIOS are also more powerful than context free rewriting rules, because of their conservative nature.

AB - An alternative hypothesis, according to which syntax is an abstraction that emerges from exposure to language, coexisting with the corpus data within the same representational mechanism is discussed. The Automatic Distillation of Structure (ADIOS) model is used which has two components which include a representational data structure, which is a directed multi graph, and a pattern acquisition (PA) algorithm that refines the graph in an unsupervised fashion. The ADIOS model incrementally learns the syntax of English from raw input by distilling structural regularities from the accrued statistical cooccurence and contextual cues. The patterns learned by ADIOS are also more powerful than context free rewriting rules, because of their conservative nature.

UR - http://www.scopus.com/inward/record.url?scp=22344442956&partnerID=8YFLogxK

M3 - ???researchoutput.researchoutputtypes.contributiontoconference.paper???

AN - SCOPUS:22344442956

SP - 61

EP - 64

T2 - 2004 AAAI Spring Symposium

Y2 - 22 March 2004 through 24 March 2004

ER -

Unsupervised context sensitive language acquisition from large, untagged corpora

Abstract

Conference

Other files and links

Fingerprint

Cite this