Peter Venable, PhD
Home: (412) 606-2387
Email: peter dot venable at alumni dot carnegie mellon dot edu
My thesis defense was Friday December 5th, 2004. I passed!
I have now moved on from Carnege Mellon to work with Haley Systems, so the rest
of this page is probably out of date.
I havent had time to update this web page because I've been busy writing
my thesis, which is titled "Modeling Syntax for Parsing
and Translation" Here's an abstract:
Syntactic structure is an important component of natural language
utterances, for both form and content. Therefore, a variety of
applications can benefit from the integration of syntax into their
statistical models of language. In this thesis, two new syntax-based
models are presented, along with their training algorithms: a
monolingual generative model of sentence structure, and a model of the
relationship between the structure of a sentence in one language and
the structure of its translation into another language. After these
models are trained and tested on the respective tasks of monolingual
parsing and word-level bilingual corpus alignment, they are
demonstrated in two additional applications. First, a new statistical
parser is automatically induced for a language in which none was
available, using a bilingual corpus. Second, a statistical
translation system is augmented with syntax-based models. Thus the
contributions of this thesis include: a statistical parsing system; a
bilingual parsing system, which infers a structural relationship
between two languages using a bilingual corpus; a method for
automatically building a parser for a language where no parser is
available; and a translation model that incorporates phrase structure.
Some of my papers are
available on the web (nothing current).
When I was at Carnegie Mellon, I worked with the Link Grammar and
I have developed a spam
filter for e-mail based on Daniel Sleator's
BLOWBACK system. Try it out! (Note: it doesn't install
itself, so it helps to know a little about perl, afs, maildelivery
to set it up).
I also have a personal homepage.