@inproceedings{luo-etal-2020-named,
title = "Named Entity Recognition Only from Word Embeddings",
author = "Luo, Ying and
Zhao, Hai and
Zhan, Junlang",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.723",
doi = "10.18653/v1/2020.emnlp-main.723",
pages = "8995--9005",
abstract = "Deep neural network models have helped named entity recognition achieve amazing performance without handcrafting features. However, existing systems require large amounts of human annotated training data. Efforts have been made to replace human annotations with external knowledge (e.g., NE dictionary, part-of-speech tags), while it is another challenge to obtain such effective resources. In this work, we propose a fully unsupervised NE recognition model which only needs to take informative clues from pre-trained word embeddings.We first apply Gaussian Hidden Markov Model and Deep Autoencoding Gaussian Mixture Model on word embeddings for entity span detection and type prediction, and then further design an instance selector based on reinforcement learning to distinguish positive sentences from noisy sentences and then refine these coarse-grained annotations through neural networks. Extensive experiments on two CoNLL benchmark NER datasets (CoNLL-2003 English dataset and CoNLL-2002 Spanish dataset) demonstrate that our proposed light NE recognition model achieves remarkable performance without using any annotated lexicon or corpus.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="luo-etal-2020-named">
<titleInfo>
<title>Named Entity Recognition Only from Word Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ying</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hai</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junlang</namePart>
<namePart type="family">Zhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Deep neural network models have helped named entity recognition achieve amazing performance without handcrafting features. However, existing systems require large amounts of human annotated training data. Efforts have been made to replace human annotations with external knowledge (e.g., NE dictionary, part-of-speech tags), while it is another challenge to obtain such effective resources. In this work, we propose a fully unsupervised NE recognition model which only needs to take informative clues from pre-trained word embeddings.We first apply Gaussian Hidden Markov Model and Deep Autoencoding Gaussian Mixture Model on word embeddings for entity span detection and type prediction, and then further design an instance selector based on reinforcement learning to distinguish positive sentences from noisy sentences and then refine these coarse-grained annotations through neural networks. Extensive experiments on two CoNLL benchmark NER datasets (CoNLL-2003 English dataset and CoNLL-2002 Spanish dataset) demonstrate that our proposed light NE recognition model achieves remarkable performance without using any annotated lexicon or corpus.</abstract>
<identifier type="citekey">luo-etal-2020-named</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.723</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.723</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>8995</start>
<end>9005</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Named Entity Recognition Only from Word Embeddings
%A Luo, Ying
%A Zhao, Hai
%A Zhan, Junlang
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F luo-etal-2020-named
%X Deep neural network models have helped named entity recognition achieve amazing performance without handcrafting features. However, existing systems require large amounts of human annotated training data. Efforts have been made to replace human annotations with external knowledge (e.g., NE dictionary, part-of-speech tags), while it is another challenge to obtain such effective resources. In this work, we propose a fully unsupervised NE recognition model which only needs to take informative clues from pre-trained word embeddings.We first apply Gaussian Hidden Markov Model and Deep Autoencoding Gaussian Mixture Model on word embeddings for entity span detection and type prediction, and then further design an instance selector based on reinforcement learning to distinguish positive sentences from noisy sentences and then refine these coarse-grained annotations through neural networks. Extensive experiments on two CoNLL benchmark NER datasets (CoNLL-2003 English dataset and CoNLL-2002 Spanish dataset) demonstrate that our proposed light NE recognition model achieves remarkable performance without using any annotated lexicon or corpus.
%R 10.18653/v1/2020.emnlp-main.723
%U https://aclanthology.org/2020.emnlp-main.723
%U https://doi.org/10.18653/v1/2020.emnlp-main.723
%P 8995-9005
Markdown (Informal)
[Named Entity Recognition Only from Word Embeddings](https://aclanthology.org/2020.emnlp-main.723) (Luo et al., EMNLP 2020)
ACL
- Ying Luo, Hai Zhao, and Junlang Zhan. 2020. Named Entity Recognition Only from Word Embeddings. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 8995–9005, Online. Association for Computational Linguistics.