Why Lexxe?
Short Question Answering: First and only search engine in the world that offers short, exact answers directly from webpages (unstructured texts only, no pre-edited question/answer databases)
Question answering technology deployed in search engines are mostly database-driven. It means the answers are pre-prepared and/or manually checked. The answer is accurate, if matched with a question. But on the other hand, it is very restrictive to factual information, particular when questions have link verbs as main verbs, e.g. "be" (is, was, are, were, etc).
Furthermore, available question answering machines in search engines return long answers with the entire sentences, very often with useless, redundant and irrelevant information usually coming in in more than a dozen and resulting in more reading time. It indicates those question answering systems may know the answers are probably inside some sentences, but not sure which words actually make the exact answer.
Lexxe is the first Internet search engine in the world that offers short, exact answers to questions. The answers are not prepared before hand. They are not from databases. The answers come from unstructured texts in the documents on the Internet and they are extracted on the fly. This will save significantly more time than key word-based searches. That's why Lexxe's overall efficiency will be a lot higher than any other search engines in the world!
Search with Key Words: Lexxe is 50% more accurate and relevant than any other search engines
You are recommended to use Lexxe because our laboratory experiments have revealed that Lexxe is 50% more accurate and relevant, and 50% more efficient than any other search engines in the world (including Google) and this efficiency rate is growing. For example, if one spent 3 minutes to find 4 pieces of information, he or she could have spent 2 minutes on Lexxe. The more one uses Lexxe (say 20 individual searches), the more obvious one will feel about Lexxe's efficiency, thanks to Lexxe's superior search accuracy in information relevance.
Clustering: Alternative Dimensions of Themes, Topics and Content Classification
One of the disadvantages of vertically ranking the search results is that one may not have a chance to capture some important information that is at the bottom of such a list. By offering clustering results on the fly, Lexxe organises information with thematic clues hidden in the texts, even they might be listed towards the end of the whole result set. The clusters can be seen as text classification of the information returned or themes that are generalised out of them. This feature can help users find something that may not appear in the snippets or re-organise the search with those cluster words/phrases.
Screening Out Irrelevant Results
Irrelevant results are usually screened out from searches, because Lexxe make search queries more focused after processing them with linguistic support. For example, if one asks about reason, like "Why is Rudolph's nose red?" (with a dozen results), the returned results could be all relevant to a reason why Ruldolph's nose is red. The number is far smaller compared to other search engines, e.g.Google (about half a million results). Screening out irrelevant results also applies to Keyword-based searches. Knowing what is relevant is vital for all search engines. However, knowing what is irrelevant is perhaps just as important and makes a search engine from good to better.
Overall: Less clicks, less reading, less searches and less time spent - more accuracy, more reliability, more intelligence and more search efficiency
By using Lexxe, less search time will be spent on and fewer searches will be made in finding the information users want. Users will make less clicks, read less and search less documents to locate the information they are looking for. That's the way Lexxe helps users to achieve search efficiency, making search a completely new experience.
One of the main features in the design of Lexxe is user convenience, which is implemented by offering both the traditional key word-based methods and the Natural Language query input in the user interface. With short answers, clusters and web site summaries as output, users can get results in any form they want or further their searches with relevant dimensions.
Search efficiency and accuracy is made possible by the 3rd Generation Search Technology invented and developed at Lexxe, which employed advanced Natural Language Processng algorithms (parsing, query understanding, query-to-search form conversion, answer type identification, key word-based search phrase recogntion, etc.) and sophisticated language data. Natural Language Processing is the key to search engine evolution and Lexxe is a pioneer in the 3rd Generation Internet search engines.
|
