[go: up one dir, main page]
Scribd
Upload
47 views20 pages

QASs Presentation

Questions Answerings Systems(QASs)

Uploaded by

soheib yahoui
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
47 views20 pages

QASs Presentation

Questions Answerings Systems(QASs)

Uploaded by

soheib yahoui
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 20

Questions Answerings

Systems
(QASs)
Realized by :
YAHOUI SOHEIB
KHIDER IMAD
TABLE OF CONTENTS
01 02 03
overview Applications of QASs NLP in QASs
Natural language
An introduction Use cases
processing
04 05 06
Architecture of QASs Algorithm of QASs conclusion
How does QASs
works
01
OVERVIEW
Question answering (QA), are a type
of systems in which a user can ask a
question using natural language, and
the system provides a concise and
correct answer.

—
overview
Example

Example
02
Applications of
QASs
Applications

Search Engines Fact checking

Google uses such systems


if a fact is verified by
to come up with questions
posing a question like:
and answers. Which is one
is fact X true or false?
of the best
Applications

technical support Customer Support Instant answers


QASs provide an question answering Many search systems
instant technical systems integrated augment their search
support into chatbots are results with instant
revolutionizing the answers, which
digital experience provide the user with
rapidly. immediate access to
information relevant
to their query.
03
NLP IN QASs
Natural language processing
NLP
The natural language question
answering systems of today often take
an extractive approach, and consist of
a retriever and a reader , . Firstly,
documents relevant to the user’s
question are loaded from a document
store. Then, the reader attempts to
extract the answer to the user’s
question.
NLP
it attempts to the relevant
terms extract in the
A reader is responsible
question. It then uses
The document store is for extracting an answer
these to retrieve relevant
responsible for providing from the documents it
documents. In order to turn
relevant documents. There receives. Using a suitable
a user’s question into the
are different ways of doing language model, it tries to
type of query ,
this. Often, a simple or understand both the
1-Removing punctuation
reverse index is used question and the
2-Removing stopwords
documents and to extract
3-Tagging entities
the most appropriate
4-Stemming
answer from the texts.

Document store retriever reader


04
Architecture of QASs
As of 2001, question answering systems typically
included a question classifier module that determines
the type of question and the type of answer.
Different types of question answering systems employ
different architectures. For example, modern open-
domain question answering systems may use a
retriever-reader architecture.
05
Algorithm of QASs
the function of the question
processing module is to candidate answers are
create some representation of extracted using all the extracting and validating
the information requested This information gathered in the answers from the set of
leads to the classification of previous steps, e.g., ordered paragraphs passed
question that include three keywords, entities and and tries to retrieve an exact
parts: Query Interface, relations. The remaining phrase to return as an
question analyzer and candidate answers are then answer to achieve this
Question classification filtered and ranked according required parsing and
This step help to generate to different measures of detailed question analysis
complex structured queries . similarity to filter out by using of answer
and detects the expected candidates with incompatible extraction algorithms
answer type of a question types

Step one Step tow Step three


06
ConcLusion
Currently we are seeing a significant shift
in the field of applied natural language
processing and neural search. Interest is
moving from the more discretized text
processing tasks like classification or
Named Entity Recognition to tasks which
test a system’s ability to truly understand
the meaning of text.We at deepset are
excited to sharing our learnings with the
broader machine learning community to
develop our question answering system!
Thanks!

You might also like