Please note this is only tagging. An important step but no
guarantee that internal structure is understood. It is still
necassary to show the ability to manipulate strings (passive
to active, question to statement, and so on) to demonstrate
the parsers understading of internal structures.
>The objectives of the parsers may be a little different but
>the comparison may still be of some interest.
>> The ESE program did manage to analyse the following sentence:
>> (3) It was mounted like a gunsight on the rim of the ship's long-range
>> antenna, and checked that the great parabolic bowl was rigidly locked upon
>> its distant target.
BracketDoctor, which gives Penn Treebank style POS tags, labeled brackets
and trees (available at http://www.ergo-ling.com) is not limited to
Junior High School Japanese textbooks like the ese and provides a better
test or our parser. The BracketDoctor is also more sophisticated than
our on-line demo.
>---- ENGCG: ----
>
>"<*it>"
> "it" <*> <NonMod> PRON NOM SG3 SUBJ @SUBJ
[snip]
>"<$2-NL>"
>
>According to what I have read the results of the morphological
>and syntactic analyzer have been successfully used in very many
>real-life applications.
This is too vague to respond to. What precisely do these
applications do?
>However, I would also like to point out that there's much more
>in the language than syntax; but that's another story
>(see, e.g., http://www.cis.hut.fi/~tho/thesis/).
Agreed, but the syntax is the basis. Modern linguistics is a
little like anceint alchemy. In anceint alchemy they were providing
accounts of complex phenomena without a proper understanding of the
building blocks of chemistry (atoms, elements, etc. and the
relationships between them). In a similar manner modern linguistics is
working on complex phenomena without having first properly understood
the basic building blocks of structure (words and the relationships
between them). The easiest and most straightforward task for linguistics
to do would be to provide a thorough account of basic structural
relationships. Then and only then is it possible to talk about
psychological reality between theories, learnability, semantics,
pragmatics and so on.
Don't get me wrong. I am not saying that modern linguistics is not
making a contribution to understanding in general, but like alchemy,
until the basic building blocks are understood their contribution
is similar to that of the alchemists.
>P.S. I am not and haven't been an employee of Lingsoft -- a comment that
> I want to make referring to the previous discussions related to the
> relationship between academic research and product marketing of the
> companies... On the other hand, I'm pleased to give some publicity
> for the recent great Finnish contributions in the area of
> information technology such as
> - Nokia mobile phones (http://www.nokia.com/company/overview/),
> - Linux operating system (http://www.cs.helsinki.fi/linux/),
> - SOM - Kohonen Self-Organizing Map (http://www.cis.hut.fi/nnrc/),
> - IRC - Internet Relay Chat (http://www.funet.fi/~irc/),
> - Ssh - Secure Shell (http://www.cs.hut.fi/ssh/), etc. etc.
It's nice to see that Finland can recognize the reality that both
industry and acadademia are crucial parts of this debate.
Phil Bralich
Philip A. Bralich, Ph.D.
President and CEO
Ergo Linguistic Technologies
2800 Woodlawn Drive, Suite 175
Honolulu, HI 96822
Tel: (808)539-3920
Fax: (808)539-3924