dirk hovy

2015/06/16, 01:12AM
NEWS: In our CoNLL paper “Cross-lingual Syntactic Variation over Age and Gender”, we show that linguistic differences between genders and age groups extend to syntax, and that certain effects hold across several languages. Draft see here

2015/06/10, 05:08AM
NEWS: Our paper “Challenges of Studying and Processing Dialects in Social Media” was accepted to W-NUT! We show that NLP tools complicate morpho-syntactic dialect studies, and present a new finding on AAVE.


“And, you know, he’s got emotional problems, man.”
“You mean… beyond pacifism?”
The Big Lebowski

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 lexical semantics (modeling what words mean in context), non-standard language, 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
2015/06/16, 01:12AM

NEWS: CoNLL Paper accepted

In our CoNLL paper “Cross-lingual Syntactic Variation over Age and Gender”, we show that linguistic differences between genders and age groups extend to syntax, and that certain effects hold across several languages. Draft see here
2015/06/10, 05:08AM

NEWS: ACL workshop paper

Our paper “Challenges of Studying and Processing Dialects in Social Media” was accepted to W-NUT! We show that NLP tools complicate morpho-syntactic dialect studies, and present a new finding on AAVE.
2015/06/10, 05:06AM

NEWS: ACL short Paper (2/2)

Our paper “If All You Have Is a Bit of the Bible: Learning Part-of-Speech Taggers for Truly Low-Resource Languages” was accepted to ACL short. We use word alignments on the Bible to propagate tags to languages w/o training data and learn models for 100 languages. Draft

Möchten Sie diese Website lieber auf deutsch lesen?

Valid XHTML 1.0 Transitional Valid CSS!