University AI Report: Applied Data Science and Google's Meena Chatbot

This report provides an analysis of Google's Meena chatbot, focusing on its implementation of artificial intelligence and data science principles. Meena, an open-domain chatbot, is designed to engage in conversations on a wide array of topics, overcoming the limitations of domain-specific chatbots. The report examines the techniques used in Meena's development, particularly natural language understanding, which enables the chatbot to interpret and generate human-like text. The architecture of Meena, based on the Evolved Transformer (ET) model, is discussed, highlighting the roles of encoder and decoder blocks in processing and generating conversational responses. The report references relevant research papers that provide insights into the advancements made by Google in the field of AI, particularly in the creation of conversational models that can initiate discussions on various subjects. The significance of Meena lies in its ability to advance the field of conversational AI and the methods that are being used to create open-domain chatbots. The analysis includes the tools and techniques involved in the development of Meena, emphasizing its importance in the domain of artificial intelligence. The report also highlights the 'sensibleness and specificity average' as a metric for evaluating the performance of these types of chatbots.

Running head: APPLIED DATA SCIENCE AND ANALYTICS
APPLIED DATA SCIENCE AND ANALYTICS
Name of the Student
Name of the University
Author Note

1APPLIED DATA SCIENCE AND ANALYTICS
Discussions
The purpose of the blog post is for the purpose of education and the topic of the blog
post is the Machine Learning that is used by Google in order to create Meena. Meena is a
chat box that can chat about anything.
The post is chosen because as days are going passing by Google is making
advancements in the field of artificial intelligence and this post is chosen in order to discuss
about the deep learning model Meena that is created by Google and the chat bot can initiate
conversations with anyone and about any type of domain (Kumar et al 2018).
The natural Language Understanding is one of the most active fields of research and it
has generated some of the best systems of AI. Most of the systems those are conversational
remain constrained to a particular domain that contrasts with the capability as humans in
order to naturally converse about various subjects (Radford et al 2018). The data science
problem that is being addressed is the constraints of the AI and they are constrained to a
particular domain. The bots that can solve this problem are the open domain chatbots. They
are replacing the Closed-Domain Chatbots.
The techniques those are used in creating Meena include natural language understand
and it is a part of the Artificial intelligence. The natural language understanding is a field of
artificial intelligence that utilises software of computer in order to understand the input that is
made in form of sentences in text or in the format of speech. Meena is a large architecture of
Evolved Transformer (So, Liang and Le 2019). Meena has a single encoder block of Evolved
Transformer and 13 decoder blocks of Evolved Transformer.
The outcomes of the data science campaign are that Google develops Meena with the
help of Natural Language Understanding that is a part of Artificial intelligence. It is one of

2APPLIED DATA SCIENCE AND ANALYTICS
the most important creations of Google. These Open-Domain Chatbots can initiate
conversation with anyone about any domains.
The chosen tools and the techniques those are used in order to create Meena is Natural
Language Understanding and it is a part of the artificial intelligence. These are also known as
open-domain chatbots and they can talk with anyone about anything. For these chatbots,
sensibleness and specificity average is a new metric. Meena is also known as model of neural
conversational (Samek, Wiegand and Müller 2017). It is ET architecture and the techniques
and tools in the ET include encoders and decoders. The encoder that is utilised is responsible
in order to process the conversation to assist Meena understand the conversation. The decoder
that is utilised in Meena then utilises that information in order to devise a response that is
actual.

3APPLIED DATA SCIENCE AND ANALYTICS
References
Kumar, V., Boorla, K., Meena, Y., Ramakrishnan, G. and Li, Y.F., 2018, June. Automating
reading comprehension by generating question and answer pairs. In Pacific-Asia Conference
on Knowledge Discovery and Data Mining (pp. 335-348). Springer, Cham.
Radford, A., Narasimhan, K., Salimans, T. and Sutskever, I., 2018. Improving language
understanding by generative pre-training. URL https://s3-us-west-2. amazonaws. com/openai-
assets/researchcovers/languageunsupervised/language understanding paper. pdf.
Samek, W., Wiegand, T. and Müller, K.R., 2017. Explainable artificial intelligence:
Understanding, visualizing and interpreting deep learning models. arXiv preprint
arXiv:1708.08296.
So, D.R., Liang, C. and Le, Q.V., 2019. The evolved transformer. arXiv preprint
arXiv:1901.11117.