scholarly journals Klasifikasi jenis kejadian menggunakan kombinasi NeuroNER dan Recurrent Convolutional Neural Network pada data Twitter

2018 ◽  
Vol 4 (2) ◽  
pp. 81
Author(s):  
Fatra Nonggala Putra ◽  
Chastine Fatichah
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Real Time ◽  
Detection System ◽  
Named Entity Recognition ◽  
Entity Recognition ◽  
Experimental Result ◽  
Incident Detection ◽  
Named Entity ◽  
F Measure

Sistem deteksi kejadian dari data Twitter bertujuan untuk mendapatkan data secara real-time sebagai alternatif sistem deteksi kejadian yang murah. Penelitian tentang sistem deteksi kejadian telah dilakukan sebelumnya. Salah satu modul utama dari sistem deteksi kejadian adalah modul klasifikasi jenis kejadian. Informasi dapat diklasifikasikan sebagai kejadian penting jika memiliki entitas yang merepresentasikan di mana lokasi kejadian terjadi. Beberapa penelitian sebelumnya masih memanfaatkan fitur ‘buatan tangan’, maupun fitur model berbasis pipeline seperti n-gram sebagai penentuan fitur kunci klasifikasi yang tidak efektif dengan performa kurang optimal. Oleh karena itu, diusulkan penggabungan metode Neuro Named Entity Recognition (NeuroNER) dan klasifier Recurrent Convolutional Neural Network (RCNN) yang diharapkan dapat melakukan deteksi kejadian secara efektif dan optimal. Pertama, sistem melakukan pengenalan entitas bernama pada data tweet untuk mengenali entitas lokasi yang terdapat dalam teks tweet, karena informasi kejadian haruslah memiliki minimal satu entitas lokasi. Kedua, jika tweet terdeteksi memiliki entitas lokasi maka akan dilakukan proses klasifikasi kejadian menggunakan klasifier RCNN. Berdasarkan hasil uji coba, disimpulkan bahwa sistem deteksi kejadian menggunakan penggabungan NeuroNER dan RCNN bekerja dengan sangat baik dengan nilai rata-rata precision, recall, dan f-measure masing-masing 94,87%, 92,73%, dan 93,73%.    The incident detection system from Twitter data aims to obtain real-time information as an alternative low-cost incident detection system. One of the main modules in the incident detection system is the classification module. Information is classified as important incident if it has an entity that represents where the incident occurred. Some previous studies still use 'handmade' features as well as feature-based pipeline models such as n-grams as the key features for classification which are deemed as ineffective. Therefore, this research propose a combination of Neuro Named Entity Recognition (NeuroNER) and Recurrent Convolutional Neural Network (RCNN) as an effective classification method for incident detection. First, the system perform named entity recognition to identify the location contained in the tweet text because the event information should have at least one location entity. Then, if the location is successfully identified, the incident will be classified using RCNN. Experimental result shows that the incident detection system using combination  of NeuroNER and RCNN works very well with the average value of precision, recall, and f-measure 92.44%, 94.76%, and 93.53% respectively.

scholarly journals Named-Entity Recognition in Sports Field Based on a Character-Level Graph Convolutional Network

Information ◽  
2020 ◽  
Vol 11 (1) ◽  
pp. 30
Author(s):  
Xieraili Seti ◽  
Aishan Wumaier ◽  
Turgen Yibulayin ◽  
Diliyaer Paerhati ◽  
Lulu Wang ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Conditional Random Fields ◽  
Structural Information ◽  
Named Entity Recognition ◽  
Entity Recognition ◽  
Convolutional Network ◽  
Named Entities ◽  
Attention Model ◽  
Named Entity

Traditional methods for identifying naming ignore the correlation between named entities and lose hierarchical structural information between the named entities in a given text. Although traditional named-entity methods are effective for conventional datasets that have simple structures, they are not as effective for sports texts. This paper proposes a Chinese sports text named-entity recognition method based on a character graph convolutional neural network (Char GCN) with a self-attention mechanism model. In this method, each Chinese character in the sports text is regarded as a node. The edge between the nodes is constructed using a similar character position and the character feature of the named-entity in the sports text. The internal structural information of the entity is extracted using a character map convolutional neural network. The hierarchical semantic information of the sports text is captured by the self-attention model to enhance the relationship between the named entities and capture the relevance and dependency between the characters. The conditional random fields classification function can accurately identify the named entities in the Chinese sports text. The results conducted on four datasets demonstrate that the proposed method improves the F-Score values significantly to 92.51%, 91.91%, 93.98%, and 95.01%, respectively, in comparison to the traditional naming methods.

Developing a RadLex-based Named Entity Recognition Tool for Mining Textual Radiology Reports (Preprint)

2020 ◽  
Author(s):  
Shintaro Tsuji ◽  
Andrew Wen ◽  
Naoki Takahashi ◽  
Hongjian Zhang ◽  
Katsuhiko Ogasawara ◽  
...  
Keyword(s):  
Named Entity Recognition ◽  
Noun Phrases ◽  
General Purpose ◽  
Entity Recognition ◽  
Free Text ◽  
Clinical Text ◽  
Named Entity ◽  
Radiology Reports ◽  
Two Measures ◽  
F Measure

BACKGROUND Named entity recognition (NER) plays an important role in extracting the features of descriptions for mining free-text radiology reports. However, the performance of existing NER tools is limited because the number of entities depends on its dictionary lookup. Especially, the recognition of compound terms is very complicated because there are a variety of patterns. OBJECTIVE The objective of the study is to develop and evaluate a NER tool concerned with compound terms using the RadLex for mining free-text radiology reports. METHODS We leveraged the clinical Text Analysis and Knowledge Extraction System (cTAKES) to develop customized pipelines using both RadLex and SentiWordNet (a general-purpose dictionary, GPD). We manually annotated 400 of radiology reports for compound terms (Cts) in noun phrases and used them as the gold standard for the performance evaluation (precision, recall, and F-measure). Additionally, we also created a compound-term-enhanced dictionary (CtED) by analyzing false negatives (FNs) and false positives (FPs), and applied it for another 100 radiology reports for validation. We also evaluated the stem terms of compound terms, through defining two measures: an occurrence ratio (OR) and a matching ratio (MR). RESULTS The F-measure of the cTAKES+RadLex+GPD was 32.2% (Precision 92.1%, Recall 19.6%) and that of combined the CtED was 67.1% (Precision 98.1%, Recall 51.0%). The OR indicated that stem terms of “effusion”, "node", "tube", and "disease" were used frequently, but it still lacks capturing Cts. The MR showed that 71.9% of stem terms matched with that of ontologies and RadLex improved about 22% of the MR from the cTAKES default dictionary. The OR and MR revealed that the characteristics of stem terms would have the potential to help generate synonymous phrases using ontologies. CONCLUSIONS We developed a RadLex-based customized pipeline for parsing radiology reports and demonstrated that CtED and stem term analysis has the potential to improve dictionary-based NER performance toward expanding vocabularies.

Sign in / Sign up

Export Citation Format

Share Document