VIETNAM NATIONAL UNIVERSITY, HANOI UNIVERSITY OF ENGINEERING AND TECHNOLOGY Nguyen Minh Trang ADVANCED DEEP LEARNING METHODS AND APPLICATIONS IN OPEN-DOMAIN QUESTION ANSWERING MASTER THESIS Major: Computer Science HA NOI - 2019 z VIETNAM NATIONAL UNIVERSITY, HANOI UNIVERSITY OF ENGINEERING AND TECHNOLOGY Nguyen Minh Trang ADVANCED DEEP LEARNING METHODS AND APPLICATIONS IN OPEN-DOMAIN QUESTION ANSWERING MASTER THESIS Major: Computer Science Supervisor: Assoc. Ha Quang Thuy Ph. Nguyen Ba Dat HA NOI - 2019 z Abstract Ever since the Internet has become ubiquitous, the amount of data accessible by information retrieval systems has increased exponentially. As for information con- sumers, being able to obtain a short and accurate answer for any query is one of the most desirable features.
This motivation, along with the rise of deep learning, has led to a boom in open-domain Question Answering (QA) research. An open- domain QA system usually consists of two modules: retriever and reader. Each is developed to solve a particular task. While the problem of document compre- hension has received multiple success with the help of large training corpora and the emergence of attention mechanism, the development of document retrieval in open-domain QA has not gain much progress.
In this thesis, we propose a novel encoding method for learning question-aware self-attentive document represen- tations. Then, these representations are utilized by applying pair-wise ranking approach to them. The resulting model is a Document Retriever, called QASA, which is then integrated with a machine reader to form a complete open-domain QA system. Our system is thoroughly evaluated using QUASAR-T dataset and shows surpassing results compared to other state-of-the-art methods.
Keywords: Open-domain Question Answering, Document Retrieval, Learning to Rank, Self-attention mechanism. iii z Acknowledgements Foremost, I would like to express my sincere gratitude to my supervisor Assoc. Ha Quang Thuy for the continuous support of my Master study and research, for his patience, motivation, enthusiasm, and immense knowledge. His guidance helped me in all the time of research and writing of this thesis.
I would also like to thank my co-supervisor Ph. Nguyen Ba Dat who has not only provided me with valuable guidance but also generously funded my re- search. My sincere thanks also goes to Assoc. Chng Eng-Siong and M.
Vu Thi Ly for offering me the summer internship opportunities in NTU, Singapore and leading me working on diverse exciting projects. I thank my fellow labmates in KTLab: M. Le Hoang Quynh, B. Can Duy Cat, B.
Tran Van Lien for the stimulating discussions, and for all the fun we have had in the last two years. Last but not the least, I would like to thank my parents for giving birth to me at the first place and supporting me spiritually throughout my life. iv z Declaration I declare that the thesis has been composed by myself and that the work has not be submitted for any other degree or professional qualification. I confirm that the work submitted is my own, except where work which has formed part of jointly- authored publications has been included.
My contribution and those of the other authors to this work have been ex- plicitly indicated below. I confirm that appropriate credit has been given within this thesis where reference has been made to the work of others. The work pre- sented in Chapter 3 was previously published in Proceedings of the 3rd ICMLSC as “QASA: Advanced Document Retriever for Open Domain Question Answering by Learning to Rank Question-Aware Self-Attentive Document Representations” by Trang M. Vu, Eng-Siong Chng.
This study was conceived by all of the authors. My contributions include: proposing the method, carrying out the experiments, and writing the paper. Master student Nguyen Minh Trang v z Table of Contents Abstract. v Table of Contents.
viii List of Figures. x List of Tables .1 Open-domain Question Answering .2 Difficulties and Challenges .3 Objectives and Thesis Outline. 8 2 Background knowledge and Related work .1 Deep learning in Natural Language Processing .2 Long Short-Term Memory network .2 Employed Deep learning techniques .1 Rectified Linear Unit activation function .2 Mini-batch gradient descent .3 Adaptive Moment Estimation optimizer .3 Pairwise Learning to Rank approach. 24 3 Material and Methods .2 Question Encoding Layer .3 Document Encoding Layer .2 Training Process and Integrated System.
39 4 Experiments and Results .1 Tools and Environment. 50 List of Publications. 52 vii z Acronyms Adam Adaptive Moment Estimation AoA Attention-over-Attention BiDAF Bi-directional Attention Flow BiLSTM Bi-directional Long Short-Term Memory CBOW Continuous Bag-Of-Words EL Embedding Layer EM Exact Match GA Gated-Attention IR Information Retrieval LSTM Long Short-Term Memory NLP Natural Language Processing QA Question Answering QASA Question-Aware Self-Attentive QEL Question Encoding Layer R3 Reinforced Ranker-Reader ReLU Rectified Linear Unit RNN Recurrent Neural Network viii z SGD Stochastic Gradient Descent TF-IDF Term Frequency – Inverse Document Frequency TREC Text Retrieval Conference ix z List of Figures 1.1 An overview of Open-domain Question Answering system.2 The pipeline architecture of an Open-domain QA system.3 The relationship among three related disciplines.4 The architecture of a simple feed-forward neural network.1 Embedding look-up mechanism.2 Recurrent Neural Network.3 Long short-term memory cell.4 Attention mechanism in the encoder-decoder architecture.5 The Rectified Linear Unit function.1 The architecture of the Document Retriever.2 The architecture of the Embedding Layer.1 Example of a question with its corresponding answer and contexts from QUASAR-T.2 Distribution of question genres (left) and answer entity-types (right).3 Top-1 accuracy on the validation dataset after each epoch.4 Loss diagram of the training dataset calculated after each epoch. 48 x z List of Tables 1.1 An example of problems encountered by the Document Retriever.4 Evaluation of retriever models on the QUASAR-T test set.5 The overall performance of various open-domain QA systems.
49 xi z Chapter 1 Introduction 1.1 Open-domain Question Answering We are living in the Information Age where many aspects of our lives are driven by information and technology. With the boom of the Internet few decades ago, there is now a colossal amount of data available and this number continues to grow exponentially. Obtaining all of these data is one thing, how to efficiently use and extract information from them is one of the most demanding requirements. Generally, the activity of acquiring useful information from a data collection is called Information Retrieval (IR).
A search engine, such as Google or Bing, is a type of IR. Search engines are extensively used that it is hard to imagine our lives today without them. Despite their applicability, current search engines and similar IR systems can only produce a list of relevant documents with respect to the user’s query. To find the exact answer needed, users still have to manually examine these documents.
Because of this, although IR systems have been handy, retrieving desirable information is still a time consuming process. The users can express their information needs in natural language instead of a series of keywords as in search engines. Furthermore, instead of a list of documents, QA systems try to return the most concise and coherent answers possible. With the vast amount of data nowadays, QA systems can reduce count- less effort in retrieving information.
Depending on usage, there are two types of QA: closed-domain and open-domain. Unlike closed-domain QA, which is re- 1 z stricted to a certain domain and requires manually constructed knowledge bases, open-domain QA aims to answer questions about basically anything. Hence, it mostly relies on world knowledge in the form of large unstructured corpora, e. Wikipedia, but databases are also used if needed.1 shows an overview of an open-domain QA system.1: An overview of Open-domain Question Answering system.
The research about QA systems has a long history tracing back to the 1960s when Green et al. [20] first proposed BASEBALL. About a decade after that, Woods et al. Both of these systems are closed-domain and they use manually defined language patterns to transform the questions into structured database queries.
Since then, knowledge bases and closed-domain QA systems had become dominant [27]. They allow users to ask questions about cer- tain things but not all. Not until the beginning of this century that open-domain QA research has become popular with the launch of the annual Text Retrieval Conference (TREC) [44] started in 1999. Ever since, TREC competitions, espe- cially the open-domain QA tracks, have progressed in size and complexity of the dataset provided, and evaluation strategies are improved.
The attention is now shifting to open-domain QA and in recent years, the number of studies on the subject has increased exceedingly.1 Problem Statement In QA systems, the questions are natural language sentences and there are a many types of them based on their semantic categories such as factoid, list, causal, confirmation, hypothetical questions, etc. The most common ones that attract most studies in the literature are factoid questions which usually begin with Wh- interrogated words, i. What, When, Where, Who [27]. With open-domain QA, the questions are not restricted to any particular domain but the users can ask whatever they want.
Answers to these questions are facts and they can simply be expressed in text format. From an overview perspective, as presented in Figure 1.1, the input and out- put of an open-domain QA system are straightforward. The input is the question, which is unrestricted, and the output is the answer, both are coherent natural lan- guage sentences and presented by text sequences. The system can use resources from the web or available databases.
Any system like this can be considered as an open-domain QA system. However, open-domain QA is usually broken down into smaller sub-tasks since being able to give concise answers to any questions is not trivial. Corresponding to each sub-task, there is a component dedicated to it. Typically, there are two sub-tasks: document retrieval and document com- prehension (or machine comprehension).
Accordingly, open-domain QA systems customarily comprise of two modules: a Document Retriever and a Document Reader. Seemingly, the Document Retriever handles the document retrieval task and the Document Reader deals with the machine comprehension task. The two modules can be integrated in a pipeline manner, e. [7, 46], to form a complete open-domain QA system.
This architecture is depicted in Figure 1.2: The pipeline architecture of an Open-domain QA system. 3 z The input of the system is still a question, namely q, and the output is an answer a. Given q, the Document Retriever acquires top-k documents from a search space by ranking them based on their relevance to q. Since the require- ment for open-domain systems is that they should be able to answer any question, the hypothetical search space is massive as it must contains the world knowledge.
However, an unlimited search space is not practical, so, knowledge sources like the Internet, or specifically Wikipidia, are commonly used. In the document re- trieval phase, a document is considered relevant to question q if it helps answer q correctly, meaning that it must at least contains the answer within its content. Nevertheless, containing the answer alone is not enough because the document returned should also be comprehensible by the Reader and consistent with the se- mantic of the question. The relevance score is quantifiable by the Retriever so that all the documents can be ranked using it.
Let D represent all documents in the search space, the set of top-k highest-scored documents is: ! D? = argmax Õ f (d, q) (1.1) X∈[D]k d∈X where f (·) is the scoring function. After obtaining a workable list of documents, D?, the Document Reader takes q and D? as input and produces an answer a which is a text span in some d j ∈ D? that gives the maximum likelihood of satisfying the question q. Unlike the Retriever, the Reader only has to handle handful number of documents. Yet, it has to examine these documents more carefully because its ultimate goal is to pin point the exact answer span from the text body.
This re- quires certain comprehending power of the Reader as well as the ability to reason and deduce.