Using deep learning for short text understanding

Abstract Classifying short texts to one category or clustering semantically related texts is challenging, and the importance of both is growing due to the rise of microblogging platforms, digital news feeds, and the like. We can accomplish this classifying and clustering with the help of a deep neural network which produces compact binary representations of a short text, and can assign the same category to texts that have similar binary representations. But problems arise when there is little contextual information on the short texts, which makes it difficult for the deep neural network to produce similar binary codes for semantically related texts. We propose to address this issue using semantic enrichment. This is accomplished by taking the nouns, and verbs used in the short texts and generating the concepts and co-occurring words with the help of those terms. The nouns are used to generate concepts within the given short text, whereas the verbs are used to prune the ambiguous context (if any) present in the text. The enriched text then goes through a deep neural network to produce a prediction label for that short text representing it’s category.