Abstract
Word association, revealing mental representations and connections of human, has been widely studied in psychology. However, the scale of available associative cue-response words is severely restricted due to the traditional manually collecting methodology. Meanwhile, with the tremendous success in Natural Language Process (NLP) tasks, an extremely large amount of plain texts can be easily acquired. This suggests an insight about the potential to find association words automatically from the text corpus instead of manually collection. As an original attempt, this paper takes a small step toward proposing a deep learning based framework for automatic association word extraction. The framework mainly consists of two stages of association word detection and machine association network construction. In particular, attention mechanism based Reading Comprehension (RC) algorithm is explored to find valuable association words automatically. To validate the value of the extracted association words, the correlation coefficient between semantic similarities of machine and human association words is introduced as an effective measurement for evaluating association consistence. The experiments are conducted on two text datasets from which together about 20k association words, more than the existing largest human association word dataset, are finally derived. The experiment further verifies that the machine association words are generally consistent with human association words with respect to semantic similarity, which highlights the promising utilization of the machine association words in the future researches of both psychology and NLP.
Highlights
What is the first responding word coming into mind when one person is given the word coffee? This is an interesting mental capability that has long been studied under the terminology Association thinking
The contributions of this paper are summarized as follows:(1) Proposing a framework of automatic association word detection from plain text based on two neural network sequential encoders with attention mechanism
EXPERIMENTS AND INSIGHTS As aforementioned, the value of extracted machine association network is mainly evaluated in terms of whether it is inherently consistent with human association network on semantic property
Summary
What is the first responding word coming into mind when one person is given the word coffee? This is an interesting mental capability that has long been studied under the terminology Association thinking. The contributions of this paper are summarized as follows:(1) Proposing a framework of automatic association word detection from plain text based on two neural network sequential encoders with attention mechanism. (2) Constructing machine association network using attention weight learned from cue-response words of two text datasets. The similarities between hidden states represented by a heat-map often reveal little information towards the decision Another line of work tends to involve human rationales in the process of understanding the decisions of attention-based models. To extract cue-response words, two neural network based sequential encoders are adopted to model the contextual and semantic information of article and comment respectively (III-A). A corpus-level association network is obtained by integrating all the document-level networks (III-C.2)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
