Advanced Google Search Tips

     As we said before in Question Answering System Phases that the second phase in an question answering system is passage retrieval. A query would be pass to GOOGLE to become documents that should contain the answer.It is recommended to pass a well formed query, so we will use GOOGLE advanced search to get a well formed query.

Some advanced Google search tips:

Google ignores common words and characters such as where, the, how, and other digits and letters which slow down your search without improving the results. We'll indicate if a word has been excluded by displaying details on the results page below the search box.

Ajeb First Seminar Presentation

SA,

Our first seminar was good Alhamdullellah, thank you all for attending and supporting.

And this is our presentation:

Feel free, write your feedback and ask any question.

Name Entity Recognition (NER)

Problem definition:

The problem of identifying proper names is particularly difficult for Arabic, since:

• Non-Vocalization: It is due to a lack of short vowels in usual texts from which a high degree of ambiguity ensues. In theory, only the Koran, and children’s books are fully vowelled.
• Lack of capitalization: The problem of identifying named entities is particularly difficult for Arabic, since names in the Arabic language do not start with capital letters and, therefore, we cannot mark them in the text by looking at the first letter of the word.
• Delimitation problems: They are related to the lack of information about unknown words with NEs, an antonomastic usage where proper names are substituted with a phrase or conversely as well as the presence of some homonyms which increases ambiguity when trying to mark NE constituents.

Question Answering System Phases

In all papers we read we found that any Question Answering system(QAS) has three common phases which are:

1. Question Analysis.
2. Passage Retrieval.
3. Answer Extraction.

And there is an addition phase we found in one paper which is "Answer Validation".

Question Analysis:

      The Question Analysis module which processes the question in order to obtain some useful information about the type of answer we are looking for and extracts the question key words and named entities.

Previous Work

English Question Answering Systems:

True Knowledge :  the True Knowledge Answer Engine attempts to comprehend posed questions by disambiguating from all possible meanings of the words in the question to find the most likely meaning of the question being asked. It does this by drawing upon its database of knowledge of discrete facts. As these facts are stored in a form that the computer can understand, the answer engine attempts to produce an answer to what it comprehends to be the question by logically deducing from them.

Wolfram Alpha : is an answer engine developed by Wolfram Research. It is an online service that answers factual queries directly by computing the answer from structured data, rather than providing a list of documents or web pages that might contain the answer as a search engine would.

The Journey Of Finding Our Project Idea

The journey started on 20/6/2010, and ended on 21/9/2010.

What? Three months! Yes it took us three months to find our golden idea.

     In July...

We collected experiences read some tips from blogs of Dr.Mohamed Samy and Alaa Shaker, asked for advices from previous experience, attended Dr. Mohamed Samy’s session about ideas in Arabic Natural Language Processing, surfed the internet, and went to companies and libraries.

Welcome Ajeb!

Ajeb our graduation project is an Arabic Question Answering System (AQAS) aiming to obtain a brief and concise answer for Arabic questions extracted from the internet corpus.

The name "Ajeb" is an Arabic do verb "أَجِـب" which means "Answer".

Our project is under the theme "ض" for Arabic NLP projects. The theme idea was suggested by Dr.Mohamed Samy.

Who are we?

We are a group of students at the faculty of computer and information sciences, computer science department at Ain Shams university, Cairo, Egypt.