Semi-supervised learning approach for Indonesian Named Entity Recognition (NER) using co-training algorithm

Aryoyudanta, Bayu; Adji, Teguh Bharata; Hidayah, Indriana

doi:10.1109/isitia.2016.7828624

Cited by 13 publications

(8 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Among the studies that solve problems in semi-supervised methods, in [36], the objective is to design a semi-supervised learning model for the NER (Indonesian Named Entity Recognition) system. NER aims to identify and classify an entity based on its context, however few instances have a label.…”

Section: Related Workmentioning

confidence: 99%

An Efficient Approach to Select Instances in Self-Training and Co-Training Semi-Supervised Methods

Vale

Gorgônio

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Semi-supervised learning is a machine learning approach that integrates supervised and unsupervised learning mechanisms. In this learning, most of labels in the training set are unknown, while there is a small part of data that has known labels. The semi-supervised learning is attractive due to its potential to use labeled and unlabeled data to perform better than supervised learning. This paper consists of a study in the field of semi-supervised learning and implements changes on two well-known semisupervised learning algorithms: self-training and co-training. In the literature, it is common to develop researches that change the structure of these algorithms, however, none of them proposes automating the labeling process of unlabeled instances, which is the main purpose of this work. In order to achieve this goal, three methods are proposed: FlexCon-G, FlexCon and FlexCon-C. The main difference among these methods is the way in which the confidence rate is calculated and the strategy used to select a label in each iteration. In order to evaluate the proposed methods' performance, an empirical analysis is conducted, in which the performance of these methods has been evaluated on 30 datasets with different characteristics. The obtained results indicate that all three proposed methods perform better than the original self-training and co-training methods, in most analysed cases.

show abstract

Section: Related Workmentioning

confidence: 99%

An Efficient Approach to Select Instances in Self-Training and Co-Training Semi-Supervised Methods

Vale

Gorgônio

et al. 2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Stemming adalah proses untuk mengurangi kata-kata yang berimbuhan menjadi bentuk dasarnya, dan hasil dari stemming ini merupakan hal yang akan menjadi dasar akan dirubahnya dari teks menjadi nominal [8].…”

Section: Teks Pre-processingunclassified

Klasifikasi Berita Menggunakan Algoritma Naive Bayes Classifer Dengan Seleksi Fitur Dan Boosting

Prakoso

Rosiyadi

Utama

et al. 2019

RESTI

View full text Add to dashboard Cite

Penelitian yang dilakukan ini merupakan bagian dari text mining untuk klasifikasi konten berita yang telah memiliki label berdasarkan katagori berita pada situs detik.com . Proses yang dilakukan adalah melakukan permodelan dan pengolahan data, mulai proses pre-processing, proses seleksi fitur information gain, dan penerapan model algoritma Naive Bayes Classifier dengan Bayesian Boosting. Hasil yang diperoleh atas model tersebut mendapatkan nilai evaluasi terhadap akurasi, recall, dan presisi sebesar 73.2%. Sedangkan dengan model yang lebih ringkas yaitu model algoritma Naive Bayes Classifier, dengan Bayesian Boosting mendapatkan nilai evaluasi yang sama besar yaitu 73.2%. Penilaian atas hasil evaluasi model yang telah terlaksankan berkesimpulan bahwa penerapan seleksi fitur Information Gain tidak berpengaruh besar atas kenaikan hasil performa terhadap kondisi label Polynomial.

show abstract

“…Supervised NER is the most commonly used approach and has attracted the greatest research effort (Nadeau and Sekine, 2007;Goyal et al, 2018), especially related to deep learning (Yadav and Bethard, 2019;Li et al, 2020). Supervised NER has performed better in F1 terms than semi-supervised in a direct comparison (Aryoyudanta et al, 2016) and on the CoNLL-2003 shared task.…”

Section: Introductionmentioning

confidence: 99%

Leveraging HTML in Free Text Web Named Entity Recognition

Ashby¹,

Weir²

2020

Proceedings of the 28th International Conference on Computational Linguistics

View full text Add to dashboard Cite

HTML tags are typically discarded in free text Named Entity Recognition from Web pages. We investigate whether these discarded tags might be used to improve NER performance. We compare Text+Tags sentences with their Text-Only equivalents, over five datasets, two free text segmentation granularities and two NER models. We find an increased F1 performance for Text+Tags of between 0.9% and 13.2% over all datasets, variants and models. This performance increase, over datasets of varying entity types, HTML density and construction quality, indicates our method is flexible and adaptable. These findings imply that a similar technique might be of use in other Web-aware NLP tasks, including the enrichment of deep language models.

show abstract

Semi-supervised learning approach for Indonesian Named Entity Recognition (NER) using co-training algorithm

Cited by 13 publications

References 9 publications

An Efficient Approach to Select Instances in Self-Training and Co-Training Semi-Supervised Methods

An Efficient Approach to Select Instances in Self-Training and Co-Training Semi-Supervised Methods

Klasifikasi Berita Menggunakan Algoritma Naive Bayes Classifer Dengan Seleksi Fitur Dan Boosting

Leveraging HTML in Free Text Web Named Entity Recognition

Contact Info

Product

Resources

About