Learning to normalize text from few examples

Grzegorz Chrupala

Learning to normalize text from few examples

Grzegorz Chrupala

Research output: Contribution to conference › Abstract › Other research output

Abstract

I propose a text normalization model based on learning edit operations from labeled data while incorporating features induced from unlabeled text and from dictionaries. These features enable effective learning with little supervision, as demonstrated on an English tweet normalization dataset.

Original language	English
Publication status	Published - 2014
Event	ATILA 2014 - Ghent, Belgium Duration: 20 Nov 2014 → 21 Nov 2014

Conference

Conference	ATILA 2014
Country/Territory	Belgium
City	Ghent
Period	20/11/14 → 21/11/14

Access to Document

http://grzegorz.chrupala.me/papers/atila-2014.pdf

Cite this

@conference{c98f56614e724412bdb3344f7c2850d6,

title = "Learning to normalize text from few examples",

abstract = "I propose a text normalization model based on learning edit operations from labeled data while incorporating features induced from unlabeled text and from dictionaries. These features enable effective learning with little supervision, as demonstrated on an English tweet normalization dataset.",

author = "Grzegorz Chrupala",

year = "2014",

language = "English",

note = "ATILA 2014 ; Conference date: 20-11-2014 Through 21-11-2014",

}

TY - CONF

T1 - Learning to normalize text from few examples

AU - Chrupala, Grzegorz

PY - 2014

Y1 - 2014

N2 - I propose a text normalization model based on learning edit operations from labeled data while incorporating features induced from unlabeled text and from dictionaries. These features enable effective learning with little supervision, as demonstrated on an English tweet normalization dataset.

AB - I propose a text normalization model based on learning edit operations from labeled data while incorporating features induced from unlabeled text and from dictionaries. These features enable effective learning with little supervision, as demonstrated on an English tweet normalization dataset.

M3 - Abstract

T2 - ATILA 2014

Y2 - 20 November 2014 through 21 November 2014

ER -

Learning to normalize text from few examples

Abstract

Conference

Access to Document

Fingerprint

Cite this