BibSonomy :: publication ::

tag user group author concept BibTeX key search:all search:diego_ma

The blue social bookmark and publication sharing system.

entry of diego_ma:

(0)

This publication has not been reviewed yet.

rating distribution

average user rating

The average rating is computed over all reviews. However, some of them may be invisible to you due to the visibility setting chosen by the reviewers.

(0.0 of 5.0 based on 0 reviews)

Orthographic Case Restoration Using Supervised Learning without Manual Annotation

by: Cheng Niu, Wei Li, Jihong, and Rohini Shrihari

In: International Journal on Artificial Intelligence Tools, Vol. 13, Nr. 1 (2004) , p. 141-156.

Resources (URL, PDF, PS...)

URL:	http://homepage.mac.com/liwei999/WeiLi/Publications.html

One challenge in text processing is the treatment of case insensitive documents such as speech recognition results. The traditional approach is to re-train a language model excluding case-related features. This paper presents an alternative two-step approach whereby a preprocessing module Step 1 is designed to restore case-sensitive form which is subsequently processed by the original system Step 2. Step 1 is mainly implemented as a Hidden Markov Model trained on a large raw corpus of case sensitive documents. It is demonstrated that this approach i outperforms the feature exclusion approach for named entity tagging, ii leads to limited degradation for parsing, relationship extraction and case insensitive question answering, iii reduces system complexity, and iv has wide applicability: the restored text can be used in both statistical model and rule-based systems.

BibTeX record

@article{Niu:2004,
  abstract = {One challenge in text processing is the treatment of case insensitive documents such as speech recognition results. The traditional approach is to re-train a language model excluding case-related features. This paper presents an alternative two-step approach whereby a preprocessing module (Step 1) is designed to restore case-sensitive form which is subsequently processed by the original system (Step 2). Step 1 is mainly implemented as a Hidden Markov Model trained on a large raw corpus of case sensitive documents. It is demonstrated that this approach (i) outperforms the feature exclusion approach for named entity tagging, (ii) leads to limited degradation for parsing, relationship extraction and case insensitive question answering, (iii) reduces system complexity, and (iv) has wide applicability: the restored text can be used in both statistical model and rule-based systems.},
  added-at = {2007-12-14T02:44:29.000+0100},
  author = {Niu, Cheng and Li, Wei and Jihong and Shrihari, Rohini},
  biburl = {http://www.bibsonomy.org/bibtex/222f9837dac4a70418136ddfff25b241d/diego_ma},
  interhash = {88217469f7bff9d742fcbcf5d3309b1d},
  intrahash = {22f9837dac4a70418136ddfff25b241d},
  journal = {International Journal on Artificial Intelligence Tools},
  keywords = {named_entities question_answering speech},
  number = 1,
  pages = {141-156},
  timestamp = {2007-12-14T02:44:29.000+0100},
  title = {Orthographic Case Restoration Using Supervised Learning without Manual Annotation},
  url = {http://homepage.mac.com/liwei999/WeiLi/Publications.html},
  volume = 13,
  year = 2004
}

Endnote record

%0 Journal Article
%1 Niu:2004
%A Niu, Cheng
%A Li, Wei
%A Jihong, 
%A Shrihari, Rohini
%D 2004
%J International Journal on Artificial Intelligence Tools
%K 
%N 1
%P 141-156
%T Orthographic Case Restoration Using Supervised Learning without Manual Annotation
%U http://homepage.mac.com/liwei999/WeiLi/Publications.html
%V 13
%X One challenge in text processing is the treatment of case insensitive documents such as speech recognition results. The traditional approach is to re-train a language model excluding case-related features. This paper presents an alternative two-step approach whereby a preprocessing module (Step 1) is designed to restore case-sensitive form which is subsequently processed by the original system (Step 2). Step 1 is mainly implemented as a Hidden Markov Model trained on a large raw corpus of case sensitive documents. It is demonstrated that this approach (i) outperforms the feature exclusion approach for named entity tagging, (ii) leads to limited degradation for parsing, relationship extraction and case insensitive question answering, (iii) reduces system complexity, and (iv) has wide applicability: the restored text can be used in both statistical model and rule-based systems.

BibSonomy :: publication ::

Orthographic Case Restoration Using Supervised Learning without Manual Annotation

Resources (URL, PDF, PS...)

Abstract

BibTeX record

Endnote record