Improving Online Forums Summarization via Hierarchical Unified Deep Neural Network
This addresses the challenge for forum participants in grasping main ideas from long threads, though it is incremental as it builds on existing deep learning techniques.
The study tackled the problem of summarizing lengthy online forum threads by proposing a Hierarchical Unified Deep Neural Network, which outperformed several competitive baselines on three datasets including real-life forums.
Online discussion forums are prevalent and easily accessible, thus allowing people to share ideas and opinions by posting messages in the discussion threads. Forum threads that significantly grow in length can become difficult for participants, both newcomers and existing, to grasp main ideas. To mitigate this problem, this study aims to create an automatic text summarizer for online forums. We present Hierarchical Unified Deep Neural Network to build sentence and thread representations for the forum summarization. In this scheme, Bi-LSTM derives a representation that comprises information of the whole sentence and whole thread; whereas, CNN captures most informative features with respect to context from sentence and thread. Attention mechanism is applied on top of CNN to further highlight high-level representations that carry important information contributing to a desirable summary. Extensive performance evaluation has been conducted on three datasets, two of which are real-life online forums and one is news dataset. The results reveal that the proposed model outperforms several competitive baselines.