Coherence-Targeted Text Summarization

This book introduces automatic text summarization approaches with improved coherence, presenting the modeling of three categories of coherence in detail – shallow content-driven coherence, deep content-driven coherence, and cognitive model-driven coherence.  The computational modeling of such coherence, coupled with proposition-level extractive summarization, works successfully for narrative text. To model coherence of different kinds, novel techniques that are suitable for different genres of text, including newswires, social media messages, and fairy tales have been developed. The extensive experimental results on benchmark or self-compiled datasets have validated the efficacy and robustness of the techniques in various circumstances. Among its many contributions to summarization, this book shows that, contrary to common belief, coherence plays a pivotal role in automatic summarization, not an ancillary one. As one of the few large-scale studies of coherence in summarization, this book heralds a complete theory of coherence and more in-depth studies in coherence-targeted text summarization.

• Text Summarization
• Content-driven Coherence
• Coherence Modeling
• Cognitive Model
• Natural Language Processing
• Computational Linguistics
• Artificial Intelligence

• Tongji University, Shanghai, China

  Renxian Zhang

Renxian Zhang is an associate professor at Tongji University. He received a PhD in Computer Science from The Hong Kong Polytechnic University, and a second PhD in Linguistics from Fudan University, China. He also worked at Samsung Electronics and is the author of more than 20 journal and conference papers on natural language processing, data mining and related areas. With in-depth knowledge of and experience in text summarization accumulated over many years, in this book the author shares his unique insights into the coherence approaches to text summarization.

Policies and ethics