Joint Modeling of Characters, Words, and Conversation Contexts for Microblog Keyphrase Extraction

Millions of messages are produced on microblog platforms every day, leading to the pressing need for automatic identification of key points from the massive texts. To absorb salient content from the vast bulk of microblog posts, this article focuses on the task of microblog keyphrase extraction. In previous work, most efforts treat messages as independent documents and might suffer from the data sparsity problem exhibited in short and informal microblog posts. On the contrary, we propose to enrich contexts via exploiting conversations initialized by target posts and formed by their replies, which are generally centered around relevant topics to the target posts and therefore helpful for keyphrase identification. Concretely, we present a neural keyphrase extraction framework, which has 2 modules: a conversation context encoder and a keyphrase tagger. The conversation context encoder captures indicative representation from their conversation contexts and feeds the representation into the keyphrase tagger, and the keyphrase tagger extracts salient words from target posts. The 2 modules were trained jointly to optimize the conversation context encoding and keyphrase extraction processes. In the conversation context encoder, we leverage hierarchical structures to capture the word‐level indicative representation and message‐level indicative representation hierarchically. In both of the modules, we apply character‐level representations, which enables the model to explore morphological features and deal with the out‐of‐vocabulary problem caused by the informal language style of microblog messages. Extensive comparison results on real‐life data sets indicate that our model outperforms state‐of‐the‐art models from previous studies.