<br><div class="gmail_quote">On Mon, Jun 1, 2009 at 12:22 PM, Eli Barzilay <span dir="ltr"><<a href="mailto:eli@barzilay.org">eli@barzilay.org</a>></span> wrote:<br><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<br><div class="im">> so I am not familiar with the alternative - would you happen to have<br>
> links or googling phrases for finding the alternatives?<br>
<br>
</div>Modern NL parsers are all statistical tools. They usually begin with<br>
a large corpus of human-parsed text, and learn how to parse more data.<br>
And there's significant work in making the learning process effective,<br>
and generalize it. The shift to this direction happened roughly<br>
during the 90s, and now I don't think that there are any practical<br>
tools that are using the symbolic approach. The bottom line is that<br>
the statistical shift makes this a very different field from what is<br>
presented in common AI books -- one thing you'll see is that there is<br>
much more "serious math" involved.<br>
<br>
</blockquote><div>Cool - thanks! <br></div></div><br>