Learning task specific distributed paragraph representations using a 2-tier convolutional neural network


We introduce a type of 2-tier convolutional neural network model for learning distributed paragraph representations for a special task (e.g. paragraph or short document level sentiment analysis and text topic categorization). We decompose the paragraph semantics into 3 cascaded constitutes: word representation, sentence composition and document composition. Specifically, we learn distributed word representations by a continuous bag-of-words model from a large unstructured text corpus. Then, using these word representations as pre-trained vectors, distributed task specific sentence representations are learned from a sentence level corpus with task-specific labels by the first tier of our model. Using these sentence representations as distributed paragraph representation vectors, distributed paragraph representations are learned from a paragraph-level corpus by the second tier of our model. It is evaluated on DBpedia ontology classification dataset and Amazon review dataset. Empirical results show the effectiveness of our proposed learning model for generating distributed paragraph representations.

Publication DOI: https://doi.org/10.1007/978-3-319-26532-2_51
Divisions: Engineering & Applied Sciences > Computer Science
Engineering & Applied Sciences > Systems analytics research institute (SARI)
Event Title: 22nd International Conference on Neural Information Processing
Event Type: Other
Event Dates: 2015-11-09 - 2015-11-12
Uncontrolled Keywords: convolutional neural network,distributed representation,natural language processing,Computer Science(all),Theoretical Computer Science
ISBN: 978-3-319-26531-5, 978-3-319-26532-2
Full Text Link: http://link.spr ... -319-26532-2_51
Related URLs: http://www.scop ... tnerID=8YFLogxK (Scopus URL)
PURE Output Type: Conference contribution
Published Date: 2015-11-12
Authors: Chen, Tao
Xu, Ruifeng
He, Yulan ( 0000-0003-3948-5845)
Wang, Xuan



Version: Accepted Version

Export / Share Citation


Additional statistics for this record