@inproceedings{jia-etal-2020-incorporating,
title = "Incorporating Uncertain Segmentation Information into {C}hinese {NER} for Social Media Text",
author = "Jia, Shengbin and
Ding, Ling and
Chen, Xiaojun and
E, Shijia and
Xiang, Yang",
editor = "Ku, Lun-Wei and
Li, Cheng-Te",
booktitle = "Proceedings of the Eighth International Workshop on Natural Language Processing for Social Media",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.socialnlp-1.7",
doi = "10.18653/v1/2020.socialnlp-1.7",
pages = "51--60",
abstract = "Chinese word segmentation is necessary to provide word-level information for Chinese named entity recognition (NER) systems. However, segmentation error propagation is a challenge for Chinese NER while processing colloquial data like social media text. In this paper, we propose a model (UIcwsNN) that specializes in identifying entities from Chinese social media text, especially by leveraging uncertain information of word segmentation. Such ambiguous information contains all the potential segmentation states of a sentence that provides a channel for the model to infer deep word-level characteristics. We propose a trilogy (i.e., Candidate Position Embedding ={\textgreater} Position Selective Attention ={\textgreater} Adaptive Word Convolution) to encode uncertain word segmentation information and acquire appropriate word-level representation. Experimental results on the social media corpus show that our model alleviates the segmentation error cascading trouble effectively, and achieves a significant performance improvement of 2{\%} over previous state-of-the-art methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jia-etal-2020-incorporating">
<titleInfo>
<title>Incorporating Uncertain Segmentation Information into Chinese NER for Social Media Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shengbin</namePart>
<namePart type="family">Jia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ling</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shijia</namePart>
<namePart type="family">E</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Xiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Workshop on Natural Language Processing for Social Media</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cheng-Te</namePart>
<namePart type="family">Li</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>Chinese word segmentation is necessary to provide word-level information for Chinese named entity recognition (NER) systems. However, segmentation error propagation is a challenge for Chinese NER while processing colloquial data like social media text. In this paper, we propose a model (UIcwsNN) that specializes in identifying entities from Chinese social media text, especially by leveraging uncertain information of word segmentation. Such ambiguous information contains all the potential segmentation states of a sentence that provides a channel for the model to infer deep word-level characteristics. We propose a trilogy (i.e., Candidate Position Embedding =\textgreater Position Selective Attention =\textgreater Adaptive Word Convolution) to encode uncertain word segmentation information and acquire appropriate word-level representation. Experimental results on the social media corpus show that our model alleviates the segmentation error cascading trouble effectively, and achieves a significant performance improvement of 2% over previous state-of-the-art methods.</abstract>
<identifier type="citekey">jia-etal-2020-incorporating</identifier>
<identifier type="doi">10.18653/v1/2020.socialnlp-1.7</identifier>
<location>
<url>https://aclanthology.org/2020.socialnlp-1.7</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>51</start>
<end>60</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Incorporating Uncertain Segmentation Information into Chinese NER for Social Media Text
%A Jia, Shengbin
%A Ding, Ling
%A Chen, Xiaojun
%A E, Shijia
%A Xiang, Yang
%Y Ku, Lun-Wei
%Y Li, Cheng-Te
%S Proceedings of the Eighth International Workshop on Natural Language Processing for Social Media
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F jia-etal-2020-incorporating
%X Chinese word segmentation is necessary to provide word-level information for Chinese named entity recognition (NER) systems. However, segmentation error propagation is a challenge for Chinese NER while processing colloquial data like social media text. In this paper, we propose a model (UIcwsNN) that specializes in identifying entities from Chinese social media text, especially by leveraging uncertain information of word segmentation. Such ambiguous information contains all the potential segmentation states of a sentence that provides a channel for the model to infer deep word-level characteristics. We propose a trilogy (i.e., Candidate Position Embedding =\textgreater Position Selective Attention =\textgreater Adaptive Word Convolution) to encode uncertain word segmentation information and acquire appropriate word-level representation. Experimental results on the social media corpus show that our model alleviates the segmentation error cascading trouble effectively, and achieves a significant performance improvement of 2% over previous state-of-the-art methods.
%R 10.18653/v1/2020.socialnlp-1.7
%U https://aclanthology.org/2020.socialnlp-1.7
%U https://doi.org/10.18653/v1/2020.socialnlp-1.7
%P 51-60
Markdown (Informal)
[Incorporating Uncertain Segmentation Information into Chinese NER for Social Media Text](https://aclanthology.org/2020.socialnlp-1.7) (Jia et al., SocialNLP 2020)
ACL