Short text Matching plays an important role in natural language processing tasks such as information retrieval (IR), question answering (QA), and dialogue system. Traditional text matching methods rely on human-crafted rules and template. Though they are effective to deal with specific situations, but lack in the ability to handle unobserved cases. In natural language, it’s infeasible to exhaust every possible expression that conveys the same ideas. Recently, neural network-based models have good generalizability to unobserved cases but provide less interpretability. In this project, we aim to balance the two sides by introducing the concept of entity to QA. We propose an interpretable, deep learning-based short text matching model for customer service domain question answering, which consists of two major components: Word segmentation enhanced Named Entity Recognition (NER), and text semantic matching. By doing so, the proposed method explicitly models entities and types of entity as building blocks of interpretable QA.
GraphBTM is a topic model which is an unsupervised algorithm to understand documents. It learns to discover the latent representation of documents and produce meaning clustering of words in the same topic. The goal of GraphBTM is to overcome the limitations of the Latent Dirichlet Allocation (LDA) which suffers from the data sparsity problem in short text and Biterm Topic Model (BTM) which claims an insufficient whole-corpus topic distribution.
The objectives of this project involve developing a customer service ontology represented as knowledge graph and building an automatic customer service system backed by the knowledge graph.
The objective of this project is to develop QIK, a fast graph-based query processing system for searching images via metadata using the concept of knowledge graphs. QIK will also recommend interesting questions to users to enable easier search.