You are on page 1of 2

WAES2108-Natural Language Processing and Generation

Azri bin Mohd Khanil


WEK110006

Assignment from Forum Discussion.

Natural language interfaces to data base management systems (e.g. Bates


1989) translate users input into a request in a formal data base query
language, and the program then proceeds as it would without the use of natural
language processing techniques.
Based on the abovementioned statement, we can say that the design of this
DBMS is similar to question answering (Q&A) systems. Discuss the differences
of these two applications.

Natural Language Interface Database


A natural language interface to a database (NLIDB) is a system that allows the user to access
information stored in a database by typing requests using natural language (e.g. English)
instead of normal database query.
Advantages of NLIDB
i.

Easy to be used - One advantage of NLIDB that the naive end-users need not
required to learn database query languages. Formal query languages are difficult to
learn and master, at least by non-computer-specialists. Graphical interfaces and formbased interfaces are easier to use by occasional users; still, invoking forms, linking
frames, selecting restrictions from menus, etc. constitute articial communication
languages that have to be learned and mastered by the end-user.

ii.

Better for some questions - It has been argued that there are kinds of questions that
can be easily expressed in natural language, but that seem difficult to express using
graphical or form-based interfaces.

iii.

Discourse - Another advantage of NLIDB, concerns natural language interfaces that


support anaphoric and elliptical expressions. NLIDB of this kind allow the use of very
brief, underspecied questions, where the meaning of each question is complemented
by the discourse context.

Disadvantages of NLIDBs
i.

Linguistic coverage not obvious - NIIDBs systems linguistic capabilities are not
obvious to the user because current Nlidbs can only cope with limited subsets of
natural language. Users find it difficult to understand (and remember) what kinds
of questions the Nlidbs can or cannot cope with.

ii.

Users assume intelligence - Nlidb users are often misled by the systems ability
to process natural language, and they assume that the system is intelligent, that it
has common sense, or that it can deduce facts, while in reality most Nlidbs have
no reasoning abilities.

Question Answering System


A question answering (QA) system aims at automatically finding concise answers to arbitrary
questions phrased in natural language. It delivers only the requested information, unlike
search engines which refer to full documents..
Advantages of Question Answering System
i.

Main advantage is human user can ask questions in natural language instead of
generating queries in a logic format.
This usage is intuitive, it saves time and allows a satisfactory result presentation even
on compact mobile devices.

ii.

Disadvantage:
i.

Context and QA

Questions are usually asked within a context and answers are provided within that specific
context. (For example, the question, "Why did Joe Biden visit Iraq in January 2010?" might
be asking why Vice President Biden visited and not President Obama).Hence ambiguity
issues need to be considered to avoid answer given out from the context and get accurate
answer needed.
ii.

Question processing

The same information request can be expressed in various ways, interrogative ("Who is the
President of the united states of America?") or assertive ("Tell me the name of the President
of the united states of America "). A semantic model of question understanding and
processing need to be used to recognize equivalent questions,

You might also like