Deep Dive Text Analytics and Natural Language Understanding

Text Insights: Natural Language Analytics for Understanding Social Media Engagement

We present Text Insights, an application for understanding factors of user engagement in Facebook pages. Providing analytics based on natural language processing, Text Insights is complementary to existing tools offering mainly numerical indicators of user engagement. Our system extracts keyphrases from page content in a linguistically motivated manner. Keyphrases are weighted according to thei...

Diagram understanding utilizing natural language text

Diagram understanding and its cooperative use with other media are important subjects in both pattern understanding and communication. However, it is quite difficult to understand diagrams without supplementary explanation by other media. For this purpose, we propose a new framework for semantic understanding of a diagram by utilizing textual information. In this framework, the elements in a di...

Text Mining by Pseudo-Natural Language Understanding

Text mining by pseudo natural language understanding (TM by PNLU for short) is a technique developed by the AST group of Chinese Academy of Sciences, as part of the project automatic knowledge acquisition by PNLU, which introduces a partial parse technique to avoid the difficulty of full NLU. It consists of three parts: PNL design, PNL parser implementation and PNLU based automatic knowledge ac...

Language Understanding for Text-based Games using Deep Reinforcement Learning

In this paper, we consider the task of learning control policies for text-based games. In these games, all interactions in the virtual world are through text and the underlying state is not observed. The resulting language barrier makes such environments challenging for automatic game players. We employ a deep reinforcement learning framework to jointly learn state representations and action po...

Natural Language Understanding in Façade: Surface-Text Processing