# 5W1H Information Extraction with CNN-Bidirectional LSTM
> Nurdin A.

URL kanonis: https://discover.unhas.ac.id/publications/pub_scopus_85045152736
Jurnal / Konferensi: Journal of Physics Conference Series
Tahun terbit: 2018
DOI: https://doi.org/10.1088/1742-6596/978/1/012078
ISSN: 17426588
Citations: 8

## Authors
- Nurdin A.

## Abstract
In this work, information about who, did what, when, where, why, and how on Indonesian news articles were extracted by combining Convolutional Neural Network and Bidirectional Long Short-Term Memory. Convolutional Neural Network can learn semantically meaningful representations of sentences. Bidirectional LSTM can analyze the relations among words in the sequence. We also use word embedding word2vec for word representation. By combining these algorithms, we obtained F-measure 0.808. Our experiments show that CNN-BLSTM outperforms other shallow methods, namely IBk, C4.5, and Naïve Bayes with the F-measure 0.655, 0.645, and 0.595, respectively.

## Keywords
- Computer science
- Word2vec
- Convolutional neural network
- Word embedding
- Artificial intelligence
- Word (group theory)
- Natural language processing
- Representation (politics)
- Measure (data warehouse)
- Sentence
- Deep learning
- Embedding
- Pattern recognition (psychology)
- Sequence (biology)
- Term (time)
- Data mining
- Mathematics
- Genetics
- Geometry
- Politics
- Physics
- Quantum mechanics
- Biology
- Law
- Political science

---
Sumber: Discover Unhas — RIMS Universitas Hasanuddin.
Saat mengutip, gunakan DOI bila tersedia atau URL kanonis di atas.