CRNN: A Joint Neural Network for Redundancy Detection

TL;DR

This paper introduces CRNN, a combined character-aware convolutional and recurrent neural network for redundancy detection, demonstrating superior performance on multiple benchmark datasets.

Contribution

The novel CRNN framework integrates Char-CNN and Char-RNN for improved sentence redundancy detection, outperforming existing methods on standard benchmarks.

Findings

CRNN achieves top F1 scores on four benchmark datasets.

Char-CNN effectively selects salient features for the RNN.

MGU offers the best runtime with comparable accuracy.

Abstract

This paper proposes a novel framework for detecting redundancy in supervised sentence categorisation. Unlike traditional singleton neural network, our model incorporates character-aware 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-art 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.