Abstract
Currently deep learning has made great breakthroughs in visual and speech processing, mainly because it draws lessons from the hierarchical mode that brain deals with images and speech. In the field of NLP, a topic model is one of the important ways for modeling documents. Topic models are built on a generative model that clearly does not match the way humans write. In this paper, we propose Event Model, which is unsupervised and based on the language processing mechanism of neurolinguistics, to model documents. In Event Model, documents are descriptions of concrete or abstract events seen, heard, or sensed by people and words are objects in the events. Event Model has two stages: word learning and dimensionality reduction. Word learning is to learn semantics of words based on deep learning. Dimensionality reduction is the process that representing a document as a low dimensional vector by a linear mode that is completely different from topic models. Event Model achieves state-of-the-art results on document retrieval tasks.
Highlights
At present, deep learning has become a popular trend in the field of machine learning
The basic assumption of topic model, followed by Replicated Softmax Model (RSM) and Deep Boltzmann Machine (DBM), is that documents are represented as random mixtures over latent topics, where each topic is characterized by a distribution over words [6]
We explore a way that the brain processes languages according to neurolinguistics and use the way to model documents, which is different from topic models
Summary
Deep learning has become a popular trend in the field of machine learning. People proposed some topic models based on the deep learning to model documents, such as Replicated Softmax Model. The basic assumption of topic model, followed by RSM and DBM, is that documents are represented as random mixtures over latent topics, where each topic is characterized by a distribution over words [6]. We explore a way that the brain processes languages according to neurolinguistics and use the way to model documents, which is different from topic models. Another approach is to use semantic association to find semantically similar words in the brain first and output. We proposed topic model based on word learning to further compare the document generating mechanisms of Event Model and topic model.
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.
