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.
Answer Bus: is an open-domain question answering system based on sentence level information retrieval. It accepts user’s natural questions in English, German, Spanish, French, Italian and Portuguese and extracts possible answers from the Web. Five search engine and directories (Google, Yahoo, WiseNut, Alta Vista and Yahoo News) are used to retrieve Web pages that contain answers. AnswerBus then extracts sentences that are contain answers
AskMSR: Microsoft is working on an “Answer Engine” that will answer common-language questions in 50 words or less using information it indexes from the Web. It’s currently called “Ask MSR,” for “Ask Microsoft Research.
Unlike other systems, AskMSR depends on data redundancy rather than linguistic analysis of questions or candidate answers. This system also explores strategies for predicting when the question answering system is likely to give wrong answer.
Arabic Question Answering Systems:
QARAB: implemented by Bassam Hammo and others, provides short answers to questions expressed in the Arabic language. The aim of the QARAB system is to identify text passages that answer natural language questions. The assumptions for the system can be summarized as follows:
- The answer exists in a collection of Arabic documents.
- The answer does not span through documents. (i.e., all supporting information for the answer lies in one document).
- The answer is a short passage.
- Processing the input question.
- Retrieving the candidate documents (paragraphs) containing answers from the IR system.
- Processing each of the candidate documents in the same way as the question is processed and returning sentences that may contain the answer.
