[Project-ideas] Query about a project idea

[Sankarshan Mukhopadhyay]

On Fri, Apr 6, 2012 at 4:11 PM, Sampoorna Biswas
<sampoorna10074 at iiitd.ac.in> wrote:

> I would like to develop a system where the query is not mapped to a
> pre-existing query, but where the processing is done upon the query itself
> in order to produce a suitable match from the data set that we are querying
> upon. It would be essentially like a multi-lingual search engine.

With a small difference. A search engine is expected to return the
accurate result. In this system, we'd be happy to respond with the
result that has the highest score of disambiguity for the language
selected to return responses in.

> What I can think of is: If we have a data set of both English and Bengali,
> first step would be to determine whether the query is in Bengali or English.
> If it is in Bengali, no translation should be required to search in the
> Bengali data set. But for the English part of it, first we can translate the
> query to English (with a high amount of accuracy) and then search. Then the
> results from both languages can be combined and presented to the user. If it
> is in English, a similar approach can be followed.
>
> However, existing machine translation systems aren't very accurate, and it
> is in fact one of the other projects in the ideas page. Should it be
> sufficient to develop such a system where the translation bit can be plugged
> in from the other project?

You needn't really wait for a perfect MT system to handle this.

/sankarshan

ps: The student proposal window closes today. And, you'll not be able
to edit it after that. So, the more you delay, the more difficult it
becomes to tune up the proposal.


-- 
sankarshan mukhopadhyay
<http://sankarshan.randomink.org/blog/>