DocTalk: Combining Dependency-Based Text Graphs and Deep Learning into a Practical Dialog Engine

Today’s deep learning dominates the field of natural language processing (NLP) with text graph-based approaches being another promising approach. However, both have inherent weaknesses. We present our system called DocTalk that brings together a model that combines the strength of the two approaches. DocTalk’s symbiotic model widens its application domain, enhanced with automatic language detection and effective multilingual summarization, keyword extraction, and question answering on several types of documents. Taking advantage of DocTalk’s flexibility, we built it into a dialog engine, coupled with an easy-to-use web interface.