A Survey Paper On Chatbots
A Survey Paper On Chatbots
A Survey Paper On Chatbots
© 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 1786
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 06 Issue: 04 | Apr 2019 www.irjet.net p-ISSN: 2395-0072
1.1 Motivation responses offered by the agent aren’t quite right. But I’m not
sure whether chatting with a bot would help me sleep, but at
Chatbots play a key role as human- computer interfaces. It’s a least it’d stop me from scrolling through the never-ending
software that simulates typed conversation, with the agenda horrors of my Twitter timeline at 4 a.m.
of temporarily luring the human into thinking they were
talking to another human. Chatbot, basically acts as a 3. UNICEF: Helping Marginalized Communities Be Heard : So
conversational agent that can talk to any user in given field far, with the exception of Endurance’s dementia companion
using the Natural Language Processing. According to World bot, the chatbots we’ve looked at have mostly been little more
Health Organization (WHO), stress is the major cause of than cool novelties. International child advocacy nonprofit
mental disorder throughout the world, posing threats to over UNICEF, however, is using chatbots to help people living in
300 million each year globally. With a rapid increase in the developing nations speak out about the most urgent needs in
need for additional assistance, the bot aims to create an their communities. The bot, called U-Report, focuses on large-
environment that is less automated and more conversational. scale data gathering via polls – this isn’t a bot for the
Thus to overcome this stress, the chatbot provides insights talkative. U-Report regularly sends out prepared polls on a
and provides positive responses through cognitive- range of urgent social issues, and users (known as “U-
behavioural therapy. Reporters”) can respond with their input. UNICEF then uses
this feedback as the basis for potential policy
1.2. Literature Survey recommendations. In one particularly striking example of
how this rather limited bot has made a major impact, U-
1. Endurance: A Companion for Dementia Patients : Many Report sent a poll to users in Liberia about whether teachers
people suffering with dementia retain much of their were coercing students into sex in exchange for better grades.
conversational abilities as their illness progresses. However, Approximately 86% of the 13,000 Liberian children U-Report
the shame and frustration that many dementia sufferers polled responded that their teachers were engaged in this
experience often make routine, everyday talks with even despicable practice, which resulted in a collaborative project
close family members challenging. That’s why Russian between UNICEF and Liberia’s Minister of Education to put
technology company Endurance developed its companion an end to it.
chat bot. Many people with Alzheimer’s disease struggle with
short-term memory loss. As such, the chatbot aims to identify 4. Med What: Making Medical Diagnoses Faster : If you’re the
deviations in conversational branches that may indicate a kind of person who has WebMD bookmarked, it might be
problem with immediate recollection – quite an ambitious worth checking out Med What.
technical challenge for an NLP-based system.
This chatbot aims to make medical diagnoses faster, easier,
In addition, since the chatbot is a cloud- based solution, and more transparent for both patients and physicians –
physicians and family members can review communication think of it like an intelligent version of WebMD that you can
logs taken from the bot to identify potential degradation of talk to. MedWhat is powered by a sophisticated machine
memory function and communicative obstacles that could learning system that offers increasingly accurate responses to
signify deterioration of the patient’s condition. Interestingly, user questions based on behaviours that it “learns” by
the as-yet unnamed conversational agent is currently an interacting with human beings. In addition to the ever-
open- source project, meaning that anyone can contribute to growing range of medical questions fielded by MedWhat, the
the development of the bot’s codebase. The project is still in bot also draws upon vast volumes of medical research and
its earlier stages, but has great potential to help scientists, peer-reviewed scientific papers to expand upon its already
researchers, and care teams better understand how considerable wealth of medical expertise. In many ways,
Alzheimer’s disease affects the brain. A Russian version of the MedWhat is much closer to a virtual assistant (like Google
bot is already available, and an English version is expected at Now) rather than a conversational agent. It also represents
some point this year. an exciting field of chatbot development that pairs intelligent
NLP systems with machine learning technology to offer users
2. Casper: Helping Insomniacs Get through the Night: an accurate and responsive experience.
If you suffer from insomnia, you’ll know that the feeling of 5. ALICE: The Bot That Launched a Thousand… Other Bots :
almost suffocating loneliness – the idea that everyone else in No list of innovative Chatbots would be complete without
the world is resting peacefully while your own mind betrays mentioning ALICE, one of the very first bots to go online – and
you with worries and doubts – is among the worst parts of one that’s held up incredibly well despite being developed
not being able to sleep. Enter Casper’s amazingly named and launched more than 20 years ago. ALICE – which stands
Insomnobot 3000 (which truly is one of the most tongue- for Artificial Linguistic Internet Computer Entity, an acronym
incheek, retro-futuristic names for a chatbot I’ve ever come that could have been lifted straight out of an episode of The X-
across), a conversational agent that aims to give insomniacs Files – was developed and launched by creator Dr. Richard
someone to talk to while the rest of the world rests easy. At Wallace way back in the dark days of the early Internet in
this point, Insomnobot 3000 is a little rudimentary. The 1995. (As you can see in the image above, the website’s
© 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 1787
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 06 Issue: 04 | Apr 2019 www.irjet.net p-ISSN: 2395-0072
© 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 1788
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 06 Issue: 04 | Apr 2019 www.irjet.net p-ISSN: 2395-0072
encoder, to predict the words of output reply. The first where in we extract the essential characteristics of
cell's job is to take in the vector representation v, and the sentences.
decide which word in its vocabulary is the most appropriate
for the output response. The second cell will be a function of Gated Recurrent Unit (GRU) aims to solve the
the vector representation v and the output of the previous vanishing gradient problem which comes with a
cell both. standard recurrent neural network. It can also be
considered as a variation on the LSTM because
both are designed similarly and, in some cases,
produce equally.
3. CONCLUSION
REFERENCES
© 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 1789