Sei sulla pagina 1di 2

A Chatbot is built to give the desired intelligent response to a natural language speech

conversation. The input to this Chatbot is keywords released from the text processing;
the output is the programmed response,

The main parameters which affect human computer interaction quality in conversational
systems design are:
(i) the techniques used to analyse the text using different grammar sets to produce
keywords,
(ii) pattern matching techniques used inside the Chatbot and depend on a variety of
database access techniques and
(iii) the type of response according to the specific application.

The text is split into separate words for tagging with parts-of-speech labels according
to their positions and neighbours in the sentence. Different types of grammar can be
used in this stage to chunk the individual tagged words in order to form phrases.
Keywords can be extracted from these phrases by eliminating unwanted words in
chinking operations. These keywords can be checked and corrected if they are not
right.

Inferring the language of a text is sometimes a necessary first step in a larger natural
language processing chain. Some languages even share homographs (e.g.room which
appears both in English and Dutch even though it has a different meaning in each
language) which may confuse algorithms with the semantics of these particular words
hence requiring the need to identify the correct language for a given text before
processing it further.

Upon receiving a new message, the chatbot has to be able to identify the goal the user
is trying to accomplish. This is usually modelled as a multi classification problem whose
labels are the names of the possible user intentions. Techniques to solve this problem
vary from simple keyword extraction to Bayesian inference inorder to determine the
user’s request based on multiple messages. LSTM networks have been previously
known to work well in this area. Those are used as well for the development of this
project.

In order to communicate, a chatbot must possess the ability to reply. Moreover, the
replies need to be coherent according to the conversation’s context.This issue can be
tackled using two different modules working in pairs : one that generates a list of
candidate replies and the other that selects the most appropriate one or ranks them
based on a certain metric. Two popular approaches have emerged from this
subproblem : retrieval-based and generative-based methods.Retrieval-based
techniques simply rely on a large database of candidate responses and matches them
with information from the user’s message to find the most ap-propriate answer. This
information can simply be a regular expression that looks for particular sentence
structures or can be the output of a machine learning modeI

Potrebbero piacerti anche