CRNN: A Joint Neural Network for Redundancy Detection

Xinyu Fu, Eugene Ch'Ng, Uwe Aickelin, Simon See

Research output: Chapter in Book/Conference proceedingConference contributionpeer-review

12 Citations (Scopus)

Abstract

This paper proposes a novel framework for detecting redundancy in supervised sentence categorisation. Unlike traditional singleton neural network, our model incorporates character- A ware convolutional neural network (Char-CNN) with character-aware recurrent neural network (Char-RNN) to form a convolutional recurrent neural network (CRNN). Our model benefits from Char-CNN in that only salient features are selected and fed into the integrated Char-RNN. Char-RNN effectively learns long sequence semantics via sophisticated update mechanism. We compare our framework against the state-of-the- A rt text classification algorithms on four popular benchmarking corpus. For instance, our model achieves competing precision rate, recall ratio, and F1 score on the Google-news data-set. For twenty-news-groups data stream, our algorithm obtains the optimum on precision rate, recall ratio, and F1 score. For Brown Corpus, our framework obtains the best F1 score and almost equivalent precision rate and recall ratio over the top competitor. For the question classification collection, CRNN produces the optimal recall rate and F1 score and comparable precision rate. We also analyse three different RNN hidden recurrent cells' impact on performance and their runtime efficiency. We observe that MGU achieves the optimal runtime and comparable performance against GRU and LSTM. For TFIDF based algorithms, we experiment with word2vec, GloVe, and sent2vec embeddings and report their performance differences.

Original languageEnglish
Title of host publication2017 IEEE International Conference on Smart Computing, SMARTCOMP 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781509065172
DOIs
Publication statusPublished - 12 Jun 2017
Event2017 IEEE International Conference on Smart Computing, SMARTCOMP 2017 - Hong Kong, China
Duration: 29 May 201731 May 2017

Publication series

Name2017 IEEE International Conference on Smart Computing, SMARTCOMP 2017

Conference

Conference2017 IEEE International Conference on Smart Computing, SMARTCOMP 2017
Country/TerritoryChina
CityHong Kong
Period29/05/1731/05/17

Keywords

  • CNN
  • GRU
  • GloVe
  • LSTM
  • MGU
  • RNN
  • Sentence classification
  • word2vec

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'CRNN: A Joint Neural Network for Redundancy Detection'. Together they form a unique fingerprint.

Cite this