Selective word encoding for effective text representation

Authors: SAVAŞ ÖZKAN, AKIN ÖZKAN

Abstract: Determining the category of a text document from its semantic content is highly motivated in the literature and it has been extensively studied in various applications. Also, the compact representation of the text is a fundamental step in achieving precise results for the applications and the studies are generously concentrated to improve its performance. In particular, the studies which exploit the aggregation of word-level representations are the mainstream techniques used in the problem. In this paper, we tackle text representation to achieve high performance in different text classification tasks. Throughout the paper, three critical contributions are presented. First, to encode the word-level representations for each text, we adapt a trainable orderless aggregation algorithm to obtain a more discriminative abstract representation by transforming word vectors to the text-level representation. Second, we propose an effective term-weighting scheme to compute the relative importance of words from the context based on their conjunction with the problem in an end-to-end learning manner. Third, we present a weighted loss function to mitigate the class-imbalance problem between the categories. To evaluate the performance, we collect two distinct datasets as Turkish parliament records (i.e. written speeches of four major political parties including 30731/7683 train and test documents) and newspaper articles (i.e. daily articles of the columnists including 16000/3200 train and test documents) whose data is available on the web. From the results, the proposed method introduces significant performance improvements to the baseline techniques (i.e. VLAD and Fisher Vector) and achieves 0.823 % and 0.878 % true prediction accuracies for the party membership and the estimation of the category of articles respectively. The performance validates that the proposed contributions (i.e. trainable word-encoding model, trainable term-weighting scheme and weighted loss function) significantly outperform the baselines.

Keywords: Text representation, orderless feature aggregation, trainable relative importance weights

Full Text: PDF