RESEARCH

HOME RESEARCH
Health Analytics
Diagnosis
Clinical Attributes
Speech and Language
Learning Lexical Coherence Representation Using LSTM Forget Gate for Children with Autism Spectrum Disorder During Story-Telling
Abstract
Inability to carry out cohesive narratives has been identified in children with autism spectrum disorder (ASD). However, deriving cohesion measures is often done using manual labeling or relying on expert-crafted features. In this work, we develop a novel LSTM framework to learn the embedded narrative cohesion representation from data directly. Our lexical coherence representation achieves a promising recognition accuracy of 92% in classifying between typically-developing (TD) and ASD children, as compared to 73% by using conventional coherence measures computed from syntactic, word usage, and latent semantic analysis. We perform additional validity analyses on our proposed representation. By experimentally introducing incoherence in the TD's story-telling narratives through word and sentence-level shuffling, the derived lexical coherence representation from these incoherent TD data samples result in a representation closer to those of ASD data samples.
Figures
It shows a complete architecture of our proposed data-driven lexical coherence representation. It includes components of: data augmentation, Chinese Word2Vec, LSTM training on Dataset II, fine-tuning on Dataset I, and finally extraction of coherence representation from LSTM forget gate.
It shows a complete architecture of our proposed data-driven lexical coherence representation. It includes components of: data augmentation, Chinese Word2Vec, LSTM training on Dataset II, fine-tuning on Dataset I, and finally extraction of coherence representation from LSTM forget gate.
Keywords
behavioral signal processing (BSP) | lexical coherence | long-short term memory neural network (LSTM) | autism spectrum disorder (ASD) | story-telling
Authors
Publication Date
2018/04/15
Conference
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
DOI
10.1109/icassp.2018.8461560
Publisher
IEEE