@inproceedings{poostchi-etal-2016-personer,
title = "{P}erso{NER}: {P}ersian Named-Entity Recognition",
author = "Poostchi, Hanieh and
Zare Borzeshi, Ehsan and
Abdous, Mohammad and
Piccardi, Massimo",
editor = "Matsumoto, Yuji and
Prasad, Rashmi",
booktitle = "Proceedings of {COLING} 2016, the 26th International Conference on Computational Linguistics: Technical Papers",
month = dec,
year = "2016",
address = "Osaka, Japan",
publisher = "The COLING 2016 Organizing Committee",
url = "https://aclanthology.org/C16-1319",
pages = "3381--3389",
abstract = "Named-Entity Recognition (NER) is still a challenging task for languages with low digital resources. The main difficulties arise from the scarcity of annotated corpora and the consequent problematic training of an effective NER pipeline. To abridge this gap, in this paper we target the Persian language that is spoken by a population of over a hundred million people world-wide. We first present and provide ArmanPerosNERCorpus, the first manually-annotated Persian NER corpus. Then, we introduce PersoNER, an NER pipeline for Persian that leverages a word embedding and a sequential max-margin classifier. The experimental results show that the proposed approach is capable of achieving interesting MUC7 and CoNNL scores while outperforming two alternatives based on a CRF and a recurrent neural network.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="poostchi-etal-2016-personer">
<titleInfo>
<title>PersoNER: Persian Named-Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hanieh</namePart>
<namePart type="family">Poostchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ehsan</namePart>
<namePart type="family">Zare Borzeshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="family">Abdous</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Massimo</namePart>
<namePart type="family">Piccardi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuji</namePart>
<namePart type="family">Matsumoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rashmi</namePart>
<namePart type="family">Prasad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The COLING 2016 Organizing Committee</publisher>
<place>
<placeTerm type="text">Osaka, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Named-Entity Recognition (NER) is still a challenging task for languages with low digital resources. The main difficulties arise from the scarcity of annotated corpora and the consequent problematic training of an effective NER pipeline. To abridge this gap, in this paper we target the Persian language that is spoken by a population of over a hundred million people world-wide. We first present and provide ArmanPerosNERCorpus, the first manually-annotated Persian NER corpus. Then, we introduce PersoNER, an NER pipeline for Persian that leverages a word embedding and a sequential max-margin classifier. The experimental results show that the proposed approach is capable of achieving interesting MUC7 and CoNNL scores while outperforming two alternatives based on a CRF and a recurrent neural network.</abstract>
<identifier type="citekey">poostchi-etal-2016-personer</identifier>
<location>
<url>https://aclanthology.org/C16-1319</url>
</location>
<part>
<date>2016-12</date>
<extent unit="page">
<start>3381</start>
<end>3389</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PersoNER: Persian Named-Entity Recognition
%A Poostchi, Hanieh
%A Zare Borzeshi, Ehsan
%A Abdous, Mohammad
%A Piccardi, Massimo
%Y Matsumoto, Yuji
%Y Prasad, Rashmi
%S Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
%D 2016
%8 December
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F poostchi-etal-2016-personer
%X Named-Entity Recognition (NER) is still a challenging task for languages with low digital resources. The main difficulties arise from the scarcity of annotated corpora and the consequent problematic training of an effective NER pipeline. To abridge this gap, in this paper we target the Persian language that is spoken by a population of over a hundred million people world-wide. We first present and provide ArmanPerosNERCorpus, the first manually-annotated Persian NER corpus. Then, we introduce PersoNER, an NER pipeline for Persian that leverages a word embedding and a sequential max-margin classifier. The experimental results show that the proposed approach is capable of achieving interesting MUC7 and CoNNL scores while outperforming two alternatives based on a CRF and a recurrent neural network.
%U https://aclanthology.org/C16-1319
%P 3381-3389
Markdown (Informal)
[PersoNER: Persian Named-Entity Recognition](https://aclanthology.org/C16-1319) (Poostchi et al., COLING 2016)
ACL
- Hanieh Poostchi, Ehsan Zare Borzeshi, Mohammad Abdous, and Massimo Piccardi. 2016. PersoNER: Persian Named-Entity Recognition. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 3381–3389, Osaka, Japan. The COLING 2016 Organizing Committee.