Professional Documents
Culture Documents
Research question: How to develop the artificial brain for dialogue systems using Neural
I. Introduction
Recently, chatbots , virtual digital assistants, becomes a trend resulting many big
intelligence, in the near future, these virtual digital assistants could replace human
roles in some areas such as customer services, ticket reservation agent or a banking
assistant.
There are several popular virtual digital assistants such as Siri from Apple,
Cortana from Microsoft, Alexa from Amazon, and Google Now from Google. These
virtual digital assistants could be used instantly from any device provided by their
companies. Rather than creating a device with an embedded virtual digital assistant,
development kit. This development kit is used to build a virtual digital assistant such
as Facebook with Wit.AI development kit and IBM with Watson development kit.
A virtual digital assistant basically is built using a conversational system
such as Natural Language Processing (NLP), Neural Network, and Deep Learning. In a
conversational system, NLP is used for recognizing natural language as an input and
and Deep Learning mostly use as a dialogue state tracker and/or a dialogue policy
manager that act as the brain or a core process to mimic a human natural response
in a conversation.
Furthermore, after the framework was decided by the purpose, this framework
from the past ten years have been selected to identify the main purpose of a
conversational system and analyze the framework used as core components. Finally,
this literature review has a focus to give brief illustration how to develop the
artificial brain for dialogue systems using Neural Networks and Generative Models.
In the next section, this literature review discusses structure in detail including
Dialogue systems were reviewed based on the framework and measurable task
From the selected articles in last decade, the used algorithms were explained for
each component. These algorithms were compared each other based on similarities
and differences to find the best approach and identify gaps for future works. This
literature review also has a purpose of identifying the gaps for future research and
MIT Artificial Intelligence Lab from 1964 to 1966. ELIZA is an early natural
Language Processing (NLP) that derived from Artificial Intelligence that focused
human input. These research use several techniques, such as rule matching,
enhance the artificial brain ability, machine learning techniques, one complex
implementation of neural network, is used to evolve the artificial brain and learn
through time.
b. Task orientation
Dialogue systems are divided into two common task oriented system, such as
i. Goal-Driven
recommendation.
dedicated task response in the end. Many systems were built using this
Most non-goal driven systems use open domain dataset from several
i. Language Understanding
based on the decoder module, another set of RNN and LSTM are used as
Seq2Seq with LSTM, and HRED Neural Network are preferred to use as
and give related parameters to dialogue policy from the current question
action values and adds word embeddings from the trained dataset to
hierarchical RNN to maps sentences into a time slot and track dialogue
state. (Serban, et al. 2016). This Recurrent Neural Network uses Gated
Recurrent Unit (GRU) memory cell as both encoder and decoder module.
On the other hand, Memory Networks offer RNN models that can
dialogue systems.
IV. Results
as decoder and encoder for language understanding and language generator. Non-
short term memory cell could be used to save input and predict a response using
memory cell is needed to maintain a longer dialogue history as parameters for task
selector. Memory Networks that offer long-term memory can be used as encoder
used to predict next response and perform task selector for given input.
V. Discussion
End-to-end dialogue systems that are used for goal-driven systems could use a
learning could improve task selector and eliminate handcrafted policy manager. In
the future, the artificial brain for dialogue systems could be composed from an
advance neural network. Deep learning, one of the machine learning techniques that
uses very complex neural network, could be implemented to simulate the artificial
VI. Conclusion
systems work and explains several models with its improvement to make the
conversational agent respond naturally to given question. Some gaps and future
works also identified from several articles to bring various methods to enhance
In this review, dialogue systems are the technology behind virtual assistants. The
dialogue systems framework is decided by the purpose of the systems. The purpose
tools.
dialogue state tracker, and policy manager. A Recurrent Neural Network encoder-
decoder with long-term memory, such as Memory Networks, and Policy Manager
Dhingra, B., et al. (2016). End-to-End Reinforcement Learning of Dialogue Agents for
Dodge, J., et al. (2015). Evaluating Prerequisite Qualities for Learning End-to-End
Dialog Systems.
Henderson, M., Thomson, B., & Young, S. (2013). Deep Neural Network Approach for
Li, J., et al. (2016b). Deep Reinforcement Learning for Dialogue Generation.
arXiv:1606.01541 [Cs].
Serban, I. V., et al. (2016). Building End-to-end Dialogue Systems Using Generative
Press.
Sutskever, I., Vinyals, O., & Le, Q. V. (2014). Sequence to Sequence Learning with