@inproceedings{li-etal-2024-corpus,
title = "A Corpus and Method for {C}hinese Named Entity Recognition in Manufacturing",
author = "Li, Ruiting and
Wang, Peiyan and
Wang, Libang and
Yang, Danqingxin and
Cai, Dongfeng",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.24/",
pages = "264--272",
abstract = "Manufacturing specifications are documents entailing different techniques, processes, and components involved in manufacturing. There is a growing demand for named entity recognition (NER) resources and techniques for manufacturing-specific named entities, with the development of smart manufacturing. In this paper, we introduce a corpus of Chinese manufacturing specifications, named MS-NERC, including 4,424 sentences and 16,383 entities. We also propose an entity recognizer named Trainable State Transducer (TST), which is initialized with a finite state transducer describing the morphological patterns of entities. It can directly recognize entities based on prior morphological knowledge without training. Experimental results show that TST achieves an overall 82.05{\%} F1 score for morphological-specific entities in zero-shot. TST can be improved through training, the result of which outperforms neural methods in few-shot and rich-resource. We believe that our corpus and model will be valuable resources for NER research not only in manufacturing but also in other low-resource domains."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2024-corpus">
<titleInfo>
<title>A Corpus and Method for Chinese Named Entity Recognition in Manufacturing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruiting</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peiyan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Libang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danqingxin</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongfeng</namePart>
<namePart type="family">Cai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Manufacturing specifications are documents entailing different techniques, processes, and components involved in manufacturing. There is a growing demand for named entity recognition (NER) resources and techniques for manufacturing-specific named entities, with the development of smart manufacturing. In this paper, we introduce a corpus of Chinese manufacturing specifications, named MS-NERC, including 4,424 sentences and 16,383 entities. We also propose an entity recognizer named Trainable State Transducer (TST), which is initialized with a finite state transducer describing the morphological patterns of entities. It can directly recognize entities based on prior morphological knowledge without training. Experimental results show that TST achieves an overall 82.05% F1 score for morphological-specific entities in zero-shot. TST can be improved through training, the result of which outperforms neural methods in few-shot and rich-resource. We believe that our corpus and model will be valuable resources for NER research not only in manufacturing but also in other low-resource domains.</abstract>
<identifier type="citekey">li-etal-2024-corpus</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.24/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>264</start>
<end>272</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Corpus and Method for Chinese Named Entity Recognition in Manufacturing
%A Li, Ruiting
%A Wang, Peiyan
%A Wang, Libang
%A Yang, Danqingxin
%A Cai, Dongfeng
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F li-etal-2024-corpus
%X Manufacturing specifications are documents entailing different techniques, processes, and components involved in manufacturing. There is a growing demand for named entity recognition (NER) resources and techniques for manufacturing-specific named entities, with the development of smart manufacturing. In this paper, we introduce a corpus of Chinese manufacturing specifications, named MS-NERC, including 4,424 sentences and 16,383 entities. We also propose an entity recognizer named Trainable State Transducer (TST), which is initialized with a finite state transducer describing the morphological patterns of entities. It can directly recognize entities based on prior morphological knowledge without training. Experimental results show that TST achieves an overall 82.05% F1 score for morphological-specific entities in zero-shot. TST can be improved through training, the result of which outperforms neural methods in few-shot and rich-resource. We believe that our corpus and model will be valuable resources for NER research not only in manufacturing but also in other low-resource domains.
%U https://aclanthology.org/2024.lrec-main.24/
%P 264-272
Markdown (Informal)
[A Corpus and Method for Chinese Named Entity Recognition in Manufacturing](https://aclanthology.org/2024.lrec-main.24/) (Li et al., LREC-COLING 2024)
ACL