dirk hovy

2015/02/21, 02:10AM
NEWS: Our paper “Mining for unambiguous instances to adapt POS taggers to new domains” finally got accepted! Thanks and congrats to my co-authors, Barbara Plank, Héctor Martínez Alonso, and Anders Søgaard!

2015/01/11, 11:02AM
BLOG: I’ll try to explain another paper I have worked on in generally understandable terms. This time, it’s about learning whose opinion we can trust.
more…


“Naja, eigentlich ist ja alles gut. Bis auf den Rest.”
Eva N.

home

Hi, glad you found this site! I work in Natural Language Processing (NLP), a subfield of artificial intelligence. My work lies at the intersection of NLP and Machine Learning. I am interested in enhancing our understanding of language with respect to two aspects: semantics (modeling what words mean in context), and co-text (the influence of extra-linguistic factors on language use). I am currently a postdoc at CST at the University of Copenhagen.
I received my PhD from the University of Southern California in Los Angeles, where I was working as research assistant at the Information Sciences Institute. My thesis topic was how to learn semantic types and relations from plain text.
You will find here

If you have questions or comments, feel free to send me a mail.
Cheers,

Dirk
2015/02/21, 02:10AM

NEWS: NAACL paper accepted

Our paper “Mining for unambiguous instances to adapt POS taggers to new domains” finally got accepted! Thanks and congrats to my co-authors, Barbara Plank, Héctor Martínez Alonso, and Anders Søgaard!
2015/01/11, 11:02AM

BLOG: What I do: Learning whom to trust

I’ll try to explain another paper I have worked on in generally understandable terms. This time, it’s about learning whose opinion we can trust.
more…
2015/01/10, 08:19AM

BLOG: What I do: Significance Testing

I get a lot of questions about what exactly it is I am doing. I usually say that I try to make computers understand language. That is of course very broad, so I decided to take a number of my papers and explain them in normal terms. This post is the first one in that series.
more…

Möchten Sie diese Website lieber auf deutsch lesen?

Valid XHTML 1.0 Transitional Valid CSS!