Adapting deep belief nets to Chinese entity detection

Zheng, Dequan; Zhao, Tiejun

doi:10.1109/mec.2013.6885350

Cited by 8 publications

(18 citation statements)

References 11 publications

(14 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some recent work on deep learning for named entity recognition include Chen et al (2010), and Passos et al (2014). Chen et al (2010) employ deep belief networks (DBN) to perform named entity categorization.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Boosting Named Entity Recognition with Neural Character Embeddings

Santos¹,

Guimarães²

2015

Proceedings of the Fifth Named Entity Workshop

199

View full text Add to dashboard Cite

Most state-of-the-art named entity recognition (NER) systems rely on handcrafted features and on the output of other NLP tasks such as part-of-speech (POS) tagging and text chunking. In this work we propose a language-independent NER system that uses automatically learned features only. Our approach is based on the CharWNN deep neural network, which uses word-level and character-level representations (embeddings) to perform sequential classification. We perform an extensive number of experiments using two annotated corpora in two different languages: HAREM I corpus, which contains texts in Portuguese; and the SPA CoNLL-2002 corpus, which contains texts in Spanish. Our experimental results give evidence of the contribution of neural character embeddings for NER. Moreover, we demonstrate that the same neural network which has been successfully applied to POS tagging can also achieve state-of-theart results for language-independet NER, using the same hyperparameters, and without any handcrafted features. For the HAREM I corpus, CharWNN outperforms the state-of-the-art system by 7.9 points in the F1-score for the total scenario (ten NE classes). For the SPA CoNLL-2002 corpus, CharWNN outperforms the state-ofthe-art system by 0.8 point in the F1.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Chen et al (2010) employ deep belief networks (DBN) to perform named entity categorization. In their system, they assume that the boundaries of all the entity mentions were previously identified, which makes their task easier than the one we tackle in this paper.…”

Section: Related Workmentioning

confidence: 99%

Boosting Named Entity Recognition with Neural Character Embeddings

Santos¹,

Guimarães²

2015

Proceedings of the Fifth Named Entity Workshop

199

View full text Add to dashboard Cite

show abstract

“…Toponym recognition is the foundation of mining these useful geo-referenced information by identifying characters, words or tokens as toponyms recognition require more features from the input sentences. Thus, DBNs were introduced into the field of toponym recognition in Chinese text, which has mainly two issues [8][9][10][11].…”

Section: Introductionmentioning

confidence: 99%

“…There are two typical models in word representation: One-Hot representation and distributed representation. The One-Hot representation model only contains the affiliation information of the characters [8,10]. It can achieve a succinct form for encoding characters or words, but will consume huge amounts of storage space and lead to the 'curse' of dimensionality.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Belief Networks Based Toponym Recognition for Chinese Text

Wang

Zhang

et al. 2018

IJGI

View full text Add to dashboard Cite

Abstract:In Geographical Information Systems, geo-coding is used for the task of mapping from implicitly geo-referenced data to explicitly geo-referenced coordinates. At present, an enormous amount of implicitly geo-referenced information is hidden in unstructured text, e.g., Wikipedia, social data and news. Toponym recognition is the foundation of mining this useful geo-referenced information by identifying words as toponyms in text. In this paper, we propose an adapted toponym recognition approach based on deep belief network (DBN) by exploring two key issues: word representation and model interpretation. A Skip-Gram model is used in the word representation process to represent words with contextual information that are ignored by current word representation models. We then determine the core hyper-parameters of the DBN model by illustrating the relationship between the performance and the hyper-parameters, e.g., vector dimensionality, DBN structures and probability thresholds. The experiments evaluate the performance of the Skip-Gram model implemented by the Word2Vec open-source tool, determine stable hyper-parameters and compare our approach with a conditional random field (CRF) based approach. The experimental results show that the DBN model outperforms the CRF model with smaller corpus. When the corpus size is large enough, their statistical metrics become approaching. However, their recognition results express differences and complementarity on different kinds of toponyms. More importantly, combining their results can directly improve the performance of toponym recognition relative to their individual performances. It seems that the scale of the corpus has an obvious effect on the performance of toponym recognition. Generally, there is no adequate tagged corpus on specific toponym recognition tasks, especially in the era of Big Data. In conclusion, we believe that the DBN-based approach is a promising and powerful method to extract geo-referenced information from text in the future.

show abstract

Chinese toponym recognition with variant neural structures from social media messages based on BERT methods

Tan

Xie

et al. 2022

J Geogr Syst

View full text Add to dashboard Cite

Many natural language tasks related to geographic information retrieval (GIR) require toponym recognition, and identifying Chinese toponyms from social media messages to share real-time information is a critical problem for many practical applications, such as natural disaster response and geolocating. In this article, we focused on toponym recognition from social media messages in Chinese. While existing off-the-shelf Chinese named entity recognition (NER) tools could be applied to identify toponyms, these approaches cannot address a variety of language irregularities taken from social media messages, including location name abbreviations, informal sentence structures and combination toponyms. We present a deep neural network named BERT-BiLSTM-CRF, which extends a basic bidirectional recurrent neural network model (BiLSTM) with the pretraining bidirectional encoder representation from transformers (BERT) representation to handle the toponym recognition task in Chinese text. Using three datasets taken from lists of alternative location names, the experimental results showed that the proposed model can significantly outperform previous Chinese NER models/algorithms and a set of state-of-the-art deep learning models.

show abstract

Adapting deep belief nets to Chinese entity detection

Cited by 8 publications

References 11 publications

Boosting Named Entity Recognition with Neural Character Embeddings

Boosting Named Entity Recognition with Neural Character Embeddings

Deep Belief Networks Based Toponym Recognition for Chinese Text

Chinese toponym recognition with variant neural structures from social media messages based on BERT methods

Contact Info

Product

Resources

About