Research of Instrument Named Entity Recognition (NER) in Research Paper Based on the Full Text

Abstract

Abstract: The full-text of research papers contain information of instruments which have not been
recorded. The effective extraction of the instrumental information from the text can be used as the basis
for quantitative research such as instrument performance evaluation. In this paper, chemical papers and
large-scale analytical instruments are taken as the object, and the unknown instrument name is found from
the literature through semantic similarity and word formation rules, the instrument name fuzzy is retrieved
for PDF typesetting, and the distinction between the actual used instruments and the unused instruments
or the entities with the same name is made based on document type, main text end identification, usage
identification words and corresponding relationship of full name abbreviation. The accuracy of such
efforts is verified by comparing with the results of manual annotation.

Fan Wuyou (Shanghai Jiao Tong University Library). Research of Instrument Named Entity Recognition (NER) in Research Paper Based on the Full Text[J]. Libraly Journal, 2022, 41(3): 126-134.

References

[ 1 ] 卢超，章成志，王玉琢，等. 语义特征分析的深
化——学术文献的全文计量分析研究综述[J].
中国图书馆学报，2021，47（2）：110–131.
[ 2 ] 张婷，安嘉璐. 基于文献计量学的药学科研仪器
发展趋势研究[J]. 中国医药导报，2014，11（12）：
129–133.
[ 3 ] 桑惠兰，唐俊峰，韩阜益. 高校大型仪器设备使
用效益评价体系的现状分析[J]. 实验室研究与
探索，2017，36（5）：281–285.
[ 4 ] 魏朝俊，闫树刚，唐剑. 高校大型精密仪器设备
使用效益的评价分析[J]. 中国现代教育装备，
2011（5）：12–14.
[ 5 ] 蒋婷 . 学术文献术语抽取方案比较研究[J]. 信息
资源管理学报，2021，11（1）：112–122.
[ 6 ] 化柏林. 针对中文学术文献的情报方法术语抽
取[J]. 现代图书情报技术，2013（6）：68–75.
[ 7 ] 夏天. 面向中文学术文本的单文档关键短语抽取[J].
数据分析与知识发现，2020，4（7）：76–86.
[ 8 ] 章成志，谢雨欣，宋云天. 学术文本中细粒度知识
实体的关联分析[J]. 图书馆论坛，2021，41（3）：
12–20.
[ 9 ] T. V. Geetha，R. Hema. Recognition of Chemical
Entities using Pattern Matching and Functional
Group Classification[J]. International Journal of
Intelligent Information Technologies （IJIIT），
2016，12（4）：21–44.
[10] Cousyn C， Bouchard K， Gaboury S， et al. Towards
Using Scientific Publications to Automatically
Extract Information on Rare Diseases[J]. Mobile Networks and Applications， 2020， 25（3）：953–
960.
[11] Spasi I， Ananiadou S. Using automatically learnt
verb selectional preferences for classification
of biomedical terms[J]. Journal of Biomedical
Informatics， 2004， 37（6）：483–497.
[12] Malgorzata Marciniak，Agnieszka Mykowiecka.
Nested term recognition driven by word connection
strength[J]. Terminology. International Journal
of Theoretical and Applied Issues in Specialized
Communication，2015，21（2）：180–204.
[13] Usié Anabel， Alves Rui， Solsona Francesc， et al.
CheNER： chemical named entity recognizer.[J].
Bioinformatics， 2014， 30（7）：1039–1040.
[14] Rockt?schel Tim， Weidlich Michael， Leser Ulf.
ChemSpot： a hybrid system for chemical named entity
recognition.[J]. Bioinformatics， 2012， 28（12）：
1633–1640.
[15] Robert Leaman，Chih-Hsuan Wei，Zhiyong
Lu. tmChem： a high performance approach
for chemical named entity recognition and
normalization[J]. Journal of Cheminformatics，
2015，7（S1）：S3.
[16] Corbett P， Boyle J. Chemlistem： Chemical named
entity recognition using recurrent neural networks[J].
Journal of Cheminformatics， 2018， 10：59.
[17] Korvigo Ilia，Holmatov Maxim，Zaikovskii
Anatolii，et al. Putting hands to rest： efficient deep
CNN-RNN architecture for chemical named entity
recognition with no hand-crafted rules.[J]. Journal of
cheminformatics，2018，10：28.
[18] Kolluru Balakrishna， Hawizy Lezan， Murray-
Rust Peter， et al. Using workflows to explore and
optimise named entity recognition for chemistry[J].
PLoS ONE， 2011， 6（5）：e20181.
[19] Tsendsuren Munkhdalai， Meijing Li， Khuyagbaatar
Batsuren， et al. Incorporating domain knowledge
in chemical and biomedical named entity
recognition with word representations.[J]. Journal of
Cheminformatics， 2015， 7（S1）：S9.
[20] Krallinger M， Leitner F， Rabal O， et al.
CHEMDNER： The drugs and chemical names
extraction challenge[J]. Journal of Cheminformatics，
2015， 7：S1.
[21] Cho H， Choi W， Lee H. A method for named
entity normalization in biomedical articles：
Application to diseases and plants[J]. BMC
Bioinformatics， 2017， 18：451.
[22] Nath N， Lee S H， Mcdonnel M， et al. The quest
for better clinical word vectors： Ontology based
and lexical vector augmentation versus clinical
contextual embeddings[J]. Computers in Biology
and Medicine， 2021， 134（2–3）：104433.
[23] PDFMiner[EB/OL]. [2014-03-24]. http://www.
unixuser.org/~euske/python/pdfminer/index.html.
[24] 杨一帆，陈文亮. 旅游场景下的实体别名抽取联
合模型[J]. 中文信息学报，2020，34（6）：55–63.
[25] models.word2vec — Word2vec embeddings. [EB/
OL]. [2021-04-16]. http://https://radimrehurek.
com/gensim/models/word2vec.html.
[26] 冯俐. 中文分词技术综述[J]. 现代计算机（专业
版），2018（34）：17–20.
[27] Levenshtein V I. Binary codes capable of correcting
deletions， insertions， and reversals. Dokl. Soviet
physics doklady， 1966， 10（8）：707–710.
[28] NLTK 3.6.2 documentation [EB/OL]. [2021-04-20].
http://www.nltk.org/.
[29] CRF++： Yet Another CRF toolkit [EB/OL]. [2013-
02-13]. http://taku910.github.io/crfpp/.
[30] ADVANCED： MAKING DYNAMIC DECISIONS
AND THE BI-LSTM CRF [EB/OL]. [2019-01-17].
https://pytorch.org/tutorials/beginner/nlp/advanced_
tutorial.html.