@inproceedings{ye-ling-2018-hybrid,
title = "Hybrid semi-{M}arkov {CRF} for Neural Sequence Labeling",
author = "Ye, Zhixiu and
Ling, Zhen-Hua",
editor = "Gurevych, Iryna and
Miyao, Yusuke",
booktitle = "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = jul,
year = "2018",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P18-2038",
doi = "10.18653/v1/P18-2038",
pages = "235--240",
abstract = "This paper proposes hybrid semi-Markov conditional random fields (SCRFs) for neural sequence labeling in natural language processing. Based on conventional conditional random fields (CRFs), SCRFs have been designed for the tasks of assigning labels to segments by extracting features from and describing transitions between segments instead of words. In this paper, we improve the existing SCRF methods by employing word-level and segment-level information simultaneously. First, word-level labels are utilized to derive the segment scores in SCRFs. Second, a CRF output layer and an SCRF output layer are integrated into a unified neural network and trained jointly. Experimental results on CoNLL 2003 named entity recognition (NER) shared task show that our model achieves state-of-the-art performance when no external knowledge is used.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ye-ling-2018-hybrid">
<titleInfo>
<title>Hybrid semi-Markov CRF for Neural Sequence Labeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhixiu</namePart>
<namePart type="family">Ye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhen-Hua</namePart>
<namePart type="family">Ling</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iryna</namePart>
<namePart type="family">Gurevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Miyao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Melbourne, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper proposes hybrid semi-Markov conditional random fields (SCRFs) for neural sequence labeling in natural language processing. Based on conventional conditional random fields (CRFs), SCRFs have been designed for the tasks of assigning labels to segments by extracting features from and describing transitions between segments instead of words. In this paper, we improve the existing SCRF methods by employing word-level and segment-level information simultaneously. First, word-level labels are utilized to derive the segment scores in SCRFs. Second, a CRF output layer and an SCRF output layer are integrated into a unified neural network and trained jointly. Experimental results on CoNLL 2003 named entity recognition (NER) shared task show that our model achieves state-of-the-art performance when no external knowledge is used.</abstract>
<identifier type="citekey">ye-ling-2018-hybrid</identifier>
<identifier type="doi">10.18653/v1/P18-2038</identifier>
<location>
<url>https://aclanthology.org/P18-2038</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>235</start>
<end>240</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hybrid semi-Markov CRF for Neural Sequence Labeling
%A Ye, Zhixiu
%A Ling, Zhen-Hua
%Y Gurevych, Iryna
%Y Miyao, Yusuke
%S Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F ye-ling-2018-hybrid
%X This paper proposes hybrid semi-Markov conditional random fields (SCRFs) for neural sequence labeling in natural language processing. Based on conventional conditional random fields (CRFs), SCRFs have been designed for the tasks of assigning labels to segments by extracting features from and describing transitions between segments instead of words. In this paper, we improve the existing SCRF methods by employing word-level and segment-level information simultaneously. First, word-level labels are utilized to derive the segment scores in SCRFs. Second, a CRF output layer and an SCRF output layer are integrated into a unified neural network and trained jointly. Experimental results on CoNLL 2003 named entity recognition (NER) shared task show that our model achieves state-of-the-art performance when no external knowledge is used.
%R 10.18653/v1/P18-2038
%U https://aclanthology.org/P18-2038
%U https://doi.org/10.18653/v1/P18-2038
%P 235-240
Markdown (Informal)
[Hybrid semi-Markov CRF for Neural Sequence Labeling](https://aclanthology.org/P18-2038) (Ye & Ling, ACL 2018)
ACL
- Zhixiu Ye and Zhen-Hua Ling. 2018. Hybrid semi-Markov CRF for Neural Sequence Labeling. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 235–240, Melbourne, Australia. Association for Computational Linguistics.