SpeedRead: A fast named entity recognition pipeline

Rami Al-Rfou; Steven Skiena

SpeedRead: A fast named entity recognition pipeline

Rami Al-Rfou
, Steven Skiena

Computer Science

Stony Brook University

Stony Brook University

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

10 Scopus citations

Abstract

Online content analysis employs algorithmic methods to identify entities in unstructured text. Both machine learning and knowledge-base approaches lie at the foundation of contemporary named entities extraction systems. However, the progress in deploying these approaches on web-scale has been been hampered by the computational cost of NLP over massive text corpora. We present SpeedRead (SR), a named entity recognition pipeline that runs at least 10 times faster than Stanford NLP pipeline. This pipeline consists of a high performance Penn Treebankcompliant tokenizer, close to state-of-art part-of-speech (POS) tagger and knowledge-based named entity recognizer.

Original language	English
Pages	51-66
Number of pages	16
State	Published - 2012
Event	24th International Conference on Computational Linguistics, COLING 2012 - Mumbai, India Duration: Dec 8 2012 → Dec 15 2012

Conference

Conference	24th International Conference on Computational Linguistics, COLING 2012
Country/Territory	India
City	Mumbai
Period	12/8/12 → 12/15/12

Keywords

NLP pipelines
Named entity recognition
Part of speech
Tokenization

Cite this

@conference{af75fa3e284745ff8008675fc2ed6a25,

title = "SpeedRead: A fast named entity recognition pipeline",

abstract = "Online content analysis employs algorithmic methods to identify entities in unstructured text. Both machine learning and knowledge-base approaches lie at the foundation of contemporary named entities extraction systems. However, the progress in deploying these approaches on web-scale has been been hampered by the computational cost of NLP over massive text corpora. We present SpeedRead (SR), a named entity recognition pipeline that runs at least 10 times faster than Stanford NLP pipeline. This pipeline consists of a high performance Penn Treebankcompliant tokenizer, close to state-of-art part-of-speech (POS) tagger and knowledge-based named entity recognizer.",

keywords = "NLP pipelines, Named entity recognition, Part of speech, Tokenization",

author = "Rami Al-Rfou and Steven Skiena",

year = "2012",

language = "English",

pages = "51--66",

note = "24th International Conference on Computational Linguistics, COLING 2012 ; Conference date: 08-12-2012 Through 15-12-2012",

}

TY - CONF

T1 - SpeedRead

T2 - 24th International Conference on Computational Linguistics, COLING 2012

AU - Al-Rfou, Rami

AU - Skiena, Steven

PY - 2012

Y1 - 2012

N2 - Online content analysis employs algorithmic methods to identify entities in unstructured text. Both machine learning and knowledge-base approaches lie at the foundation of contemporary named entities extraction systems. However, the progress in deploying these approaches on web-scale has been been hampered by the computational cost of NLP over massive text corpora. We present SpeedRead (SR), a named entity recognition pipeline that runs at least 10 times faster than Stanford NLP pipeline. This pipeline consists of a high performance Penn Treebankcompliant tokenizer, close to state-of-art part-of-speech (POS) tagger and knowledge-based named entity recognizer.

AB - Online content analysis employs algorithmic methods to identify entities in unstructured text. Both machine learning and knowledge-base approaches lie at the foundation of contemporary named entities extraction systems. However, the progress in deploying these approaches on web-scale has been been hampered by the computational cost of NLP over massive text corpora. We present SpeedRead (SR), a named entity recognition pipeline that runs at least 10 times faster than Stanford NLP pipeline. This pipeline consists of a high performance Penn Treebankcompliant tokenizer, close to state-of-art part-of-speech (POS) tagger and knowledge-based named entity recognizer.

KW - NLP pipelines

KW - Named entity recognition

KW - Part of speech

KW - Tokenization

UR - https://www.scopus.com/pages/publications/84876814046

M3 - Paper

SP - 51

EP - 66

Y2 - 8 December 2012 through 15 December 2012

ER -

SpeedRead: A fast named entity recognition pipeline

Abstract

Conference

Keywords

Other files and links

Fingerprint

Cite this