Dense Word Representation Utilization in Indonesian Dependency Parsing

Available Indonesian dependency parsers can be considered worse than other languages’ parsers that have been researched thoroughly. Currently, Indonesia dependency parsers can’t reliably parse sentences with gerund(s) and/or ellipsis correctly. This is because of the sparse feature representation that causes difficulty in parsing these types of sentences. In this research, dense representation is proposed for Indonesian dependency parser. The use of dense word representation may allow better generalization and gives more information regarding the words to be parsed, which allows a more accurate parsing. The scope of the dependency parsing in this research is limited to well-formed Indonesian sentences, using the local transition-based parsing. Based on our experiments, we found that using word embedding instead of sparse word representation increases parsing accuracy significantly.

Effective Crack Damage Detection Using Multilayer Sparse Feature Representation and Incremental Extreme Learning Machine

Detecting cracks within reinforced concrete is still a challenging problem, owing to the complex disturbances from the background noise. In this work, we advocate a new concrete crack damage detection model, based upon multilayer sparse feature representation and an incremental extreme learning machine (ELM), which has both favorable feature learning and classification capabilities. Specifically, by cropping and using a sliding window operation and image rotation, a large number of crack and non-crack patches are obtained from the collected concrete images. With the existing image patches, the defect region features can be quickly calculated by the multilayer sparse ELM autoencoder networks. Then, the online incremental ELM classified network is used to recognize the crack defect features. Unlike the commonly-used deep learning-based methods, the presented ELM-based crack detection model can be trained efficiently without tediously fine-tuning the entire-network parameters. Moreover, according to the ELM theory, the proposed crack detector works universally for defect feature extraction and detection. In the experiments, when compared with other recently developed crack detectors, the proposed concrete crack detection model can offer outstanding training efficiency and favorable crack detecting accuracy.