Deep Learning for Learning Representation and Its Application to Natural Language Processing

As the web evolves even faster than expected, the exponential growth of data becomes overwhelming. Textual data is being generated at an ever-increasing pace via emails, documents on the web, tweets, online user reviews, blogs, and so on. As the amount of unstructured text data grows, so does the need for intelligently processing and understanding it. The focus of this dissertation is on developing learning models that automatically induce representations of human language to solve higher level language tasks. In contrast to most conventional learning techniques, which employ certain shallow-structured learning architectures, deep learning is a newly developed machine learning technique which uses supervised and/or unsupervised strategies to automatically learn hierarchical representations in deep architectures and has been employed in varied tasks such as classification or regression. Deep learning was inspired by biological observations on human brain mechanisms for processing natural signals and has attracted the tremendous attention of both academia and industry in recent years due to its state-of-the-art performance in many research domains such as computer vision, speech recognition, and natural language processing. This dissertation focuses on how to represent the unstructured text data and how to model it with deep learning models in different natural language processing viii applications such as sequence tagging, sentiment analysis, semantic similarity and etc. Specifically, my dissertation addresses the following research topics: In Chapter 3, we examine one of the fundamental problems in NLP, text classification, by leveraging contextual information [MLX18a]; In Chapter 4, we propose a unified framework for generating an informative map from review corpus [MLX18b]; Chapter 5 discusses the tagging address queries in map search [Mok18]. This research was performed in collaboration with Microsoft; and In Chapter 6, we discuss an ongoing research work in the neural language sentence matching problem. We are working on extending this work to a recommendation system