LDA in Character-LSTM-CRF Named Entity Recognition

被引：1

作者：

Konopik, Miloslav ^{[1
]}

Prazak, Ondrej ^{[1
]}

机构：

[1] Univ West Bohemia, Fac Appl Sci, Dept Comp Sci & Engn, Univ 8, Plzen 30614, Czech Republic

来源：

TEXT, SPEECH, AND DIALOGUE (TSD 2018) | 2018年 / 11107卷

关键词：

Named entity recognition; LSTM; LDA; Tensorflow;

D O I：

10.1007/978-3-030-00794-2_6

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we present a NER system based upon deep learning models with character sequence encoding and word sequence encoding in LSTM layers. The results are boosted with LDA topic models and linear-chain CRF sequence tagging. We reach the new state-ofthe-art performance in NER of 81.77 F-measure for Czech and 85.91 F-measure Spanish.

引用

页码：58 / 66

页数：9

共 15 条

[1]

Abadi M, 2016, PROCEEDINGS OF OSDI'16: 12TH USENIX SYMPOSIUM ON OPERATING SYSTEMS DESIGN AND IMPLEMENTATION, P265

[2] Robust multilingual Named Entity Recognition with shallow semi-supervised features [J].

Agerri, Rodrigo ;

Rigau, German .

ARTIFICIAL INTELLIGENCE, 2016, 238 :63-82

[3]

[Anonymous], 2002, MALLET: A machine learning for language toolkit

[4]

[Anonymous], 2016, CORR

[5] Latent Dirichlet allocation [J].

Blei, DM ;

Ng, AY ;

Jordan, MI .

JOURNAL OF MACHINE LEARNING RESEARCH, 2003, 3 (4-5) :993-1022

[6]

Chiu J. P., 2016, Trans. Assoc. Comput. Linguist., V4, P357, DOI DOI 10.1162/TACLA00104

[7]

dos Santos Ccero., 2015, Proceedings of NEWS 2015 The Fifth Named Entities Workshop, P25

[8]

Erik F, 2002, P CONLL 2002, V20, P1

[9] Latent semantics in Named Entity Recognition [J].

Konkol, Michal ;

Brychcin, Tomas ;

Konopik, Miloslav .

EXPERT SYSTEMS WITH APPLICATIONS, 2015, 42 (07) :3470-3479

[10]

Konkol M, 2013, LECT NOTES COMPUT SC, V8082, P153, DOI 10.1007/978-3-642-40585-3_20

← 1 2 →