Is there any simple explanation how Watson finds and scores evidence after gathering massive evidence and analyzing the data?
In other words, how does it know which precise answer it needs to return?
$\begingroup$
$\endgroup$
Add a comment
|
2 Answers
$\begingroup$
$\endgroup$
Watson starts off by searching its massive database of sources for stuff that might be pertinent to the question. Next, it searches through all of the search results and turns them into candidate answers. For example, if one of the search results is an article, Watson might pick the title of the article as a possible answer. After finding all of these candidate answers, it proceeds to iteratively score them to determine which one is best.
The scoring process is very complicated, and involves finding supporting evidence for each answer, and then combining many different scoring algorithms to determine which candidate answer is the best. You can read a more detailed (but still very conceptual) overview here, by the creators of Watson.
$\begingroup$
$\endgroup$
0
IBM clearly don't provide all the details / "secret sauce" but there is some information out there on how Watson works. Some of the text search / retrieval stuff uses a technology called UIMA which IBM open-sourced a few years ago. It also uses Prolog and some custom C++ code. Some more information can be found here.
