dirk hovy

2016/10/22, 04:59AM
BLOG: I had some time and analyzed the US presidential debates from a quantitative point of view. Turns out the candidates differ even beyond their messages.
more…

2016/09/15, 06:25AM
NEWS: I am proud and happy to announce that as of Aug 1, I am associate professor of computer science at the computer science department of the University of Copenhagen. The goal of a 15-year journey :)


“If at first you don’t succeed, that’s one data point.”
xkcd

portfolio

My research focuses on computational sociolinguistics, i.e., the intersection of sociolinguistics and statistical natural language processing (NLP). I am motivated by the influence of social dimensions on both language and engineering decisions, for instance: how do age differences affect part-of-speech tagging accuracy? Language encodes socio-demographic differences (age, gender, etc.), but current NLP models assume all language is homogenous. This assumption generates demographically biased models that perform poorly on data from demographic groups which do not match the training data. The goal of my research is to integrate sociolinguistic knowledge into NLP models. Concretely, I use large-scale statistics to detect and model the interaction between people’s demographic profile and their language use (see here or here). The potential impact of addressing demographic bias benefits society, industry, and research. I am also interested in semantics (modeling what words mean in context, see here, here, or here), and non-standard language (see here, here, here or here).
The following papers can be downloaded as PDF files.

NB: Papers in Natural Language Processing are usually published at conferences, due to the rapid development of the field. Each publication is typically reviewed by at least three reviewers. Acceptance rates are given wherever available. Author order typically reflects work load and responsibility.

2017

  1. Dirk Hovy, Shannon Spruit, Margaret Mitchell, Emily M. Bender, Michael Strube, and Hanna Wallach: Proceedings of the First ACL Workshop on Ethics in Natural Language Processing. EACL, 2017.
    [Abstract]  [PDF]
  2. Adrian Benton, Margaret Mitchell, and Dirk Hovy: Multitask Learning for Mental Health Conditions with Limited Social Media Data. EACL, 2017.
    [Abstract]  [PDF]

2016

  1. Astrid Ravn Skovse, Dirk Hovy, and Anders Johannsen: Mapping sense(s) of place. Sociolinguistic Symposium, 2016.
    [Abstract]  [PDF]
  2. David Bamman, A. Seza Doğruöz, Jacob Eisenstein, Dirk Hovy, David Jurgens, Brendan O'Connor, Alice Oh, Oren Tsur, Svitlana Volkova: Proceedings of the First Workshop on NLP and Computational Social Science (NLPandCSS). EMNLP, 2016.
    [Abstract]  [PDF]
  3. Nathan Schneider, Dirk Hovy, Anders Johannsen, and Marine Carpuat: SemEval-2016 Task 10: Detecting Minimal Semantic Units and their Meanings (DiMSUM). SemEval, 2016.
    [Abstract]  [PDF]
  4. Dirk Hovy and Shannon L. Spruit: The Social Impact of Natural Language Processing. ACL short, 2016 (acceptance rate 22%).
    [Abstract]  [PDF]
  5. Dirk Hovy: The Enemy in Your Own Camp: How Well Can We Detect Statistically-Generated Fake Reviews - An Adversarial Study. ACL short, 2016 (acceptance rate 22%).
    [Abstract]  [PDF]
  6. Gavin Abercrombie and Dirk Hovy: Putting Sarcasm Detection into Context: The Effects of Class Imbalance and Manual Labelling on Supervised Machine Classification of Twitter Conversations. ACL SRW, 2016.
    [Abstract]  [PDF]
  7. Zeerak Waseem and Dirk Hovy: Hateful Symbols or Hateful People? Predictive Features for Hate Speech Detection on Twitter. NAACL SRW, 2016.
    [Abstract]  [PDF]
  8. Anna Jørgensen, Dirk Hovy, and Anders Søgaard: Learning a POS tagger for AAVE-like language. NAACL, 2016 (acceptance rate 29%).
    [Abstract]  [PDF]
  9. Rebekah Tromble and Dirk Hovy: These 6 charts show how much sexism Hillary Clinton faces on Twitter. Washington Post. Monkey Cage, 2016.
    [Abstract]  [PDF]
  10. Dirk Hovy and Anders Johannsen: Exploring Language Variation Across Europe. A Web-based Tool for Computational Sociolinguistics. LREC, 2016.
    [Abstract]  [PDF]

2015

  1. Lasse Borgholm, Peter Simonsen, and Dirk Hovy: The Rating Game: Sentiment Rating Reproducibility from Text. EMNLP, 2015 (acceptance rate 24%).
    [Abstract]  [PDF]
  2. Barbara Plank and Dirk Hovy: Personality Traits on Twitter -or- How to Get 1500 Personality Tests in a Week. WASSA, 2015.
    [Abstract]  [PDF]
  3. Anders Johannsen, Dirk Hovy, and Anders Søgaard: Cross-lingual Syntactic Variation over Age and Gender. CoNLL, 2015 (acceptance rate 29.9%).
    [Abstract]  [PDF]
  4. Dirk Hovy and Anders Søgaard: Tagging Performance Correlates Negatively with Author Age. ACL short, 2015 (acceptance rate 22.4%).
    [Abstract]  [PDF]
  5. Željko Agić, Dirk Hovy, and Anders Søgaard: If All You Have Is a Bit of the Bible: Learning Part-of-Speech Taggers for Truly Low-Resource Languages. ACL short, 2015 (acceptance rate 22.4%).
    [Abstract]  [PDF]
  6. Anna Jørgensen, Dirk Hovy, and Anders Søgaard: Challenges of Studying and Processing Dialects in Social Media. ACL Workshop on Noisy User-generated Text, 2015.
    [Abstract]  [PDF]
  7. Dirk Hovy: Demographic Factors Improve Classification Performance. ACL long, 2015 (acceptance rate 25%).
    [Abstract]  [PDF]
  8. Dirk Hovy, Barbara Plank, Héctor Martínez Alonso, and Anders Søgaard: Mining for unambiguous instances to adapt POS taggers to new domains. NAACL short, 2015 (acceptance rate 22.1%).
    [Abstract]  [PDF]
  9. Dirk Hovy, Anders Johannsen, and Anders Søgaard: User review sites as a resource for large-scale sociolinguistic studies. WWW, 2015 (acceptance rate 14%).
    [Abstract]  [PDF]

2014

  1. Barbara Plank, Dirk Hovy, Ryan McDonald, and Anders Søgaard: Adapting taggers to Twitter with (less) distant supervision. Coling, 2014 (acceptance rate 31%).
    [Abstract]  [PDF]
  2. Natalie Schluter, Anders Søgaard, Jakob Elming, Dirk Hovy, Barbara Plank, Héctor Martínez Alonso, Anders Johannsen, and Sigrid Klerke: Copenhagen-Malmö: Tree approximations of semantic parsing problems. SemEval, 2014.
    [Abstract]  [PDF]
  3. Anders Johannsen, Dirk Hovy, Héctor Martínez Alonso, Barbara Plank, and Anders Søgaard: More or less supervised super-sense tagging of Twitter. *SEM (Best Paper), 2014.
    [Abstract]  [PDF]
  4. Dirk Hovy: How Well can We Learn Interpretable Entity Types from Text?. ACL, 2014 (acceptance rate 26%).
    [Abstract]  [PDF]
  5. Dirk Hovy, Barbara Plank, and Anders Søgaard: Experiments with crowdsourced re-annotation of a POS tagging data set. ACL, 2014 (acceptance rate 26%).
    [Abstract]  [PDF]
  6. Barbara Plank, Dirk Hovy, and Anders Søgaard: Linguistically debatable or just plain wrong?. ACL, 2014 (acceptance rate 26%).
    [Abstract]  [PDF]
  7. Anders Søgaard, Anders Johannsen, Barbara Plank, Dirk Hovy, and Héctor Martínez Alonso: What’s in a p-value in NLP?. CoNLL, 2014.
    [Abstract]  [PDF]
  8. Jakob Elming, Barbara Plank, and Dirk Hovy: Robust Cross-Domain Sentiment Analysis for Low-Resource Languages. ACL, WASSA, 2014.
    [Abstract]  [PDF]
  9. Barbara Plank, Dirk Hovy, and Anders Søgaard: Learning POS taggers with inter-annotator agreement loss. EACL (Best Paper), 2014 (acceptance rate 25%).
    [Abstract]  [PDF]
  10. Dirk Hovy, Barbara Plank, and Anders Søgaard: When POS datasets don’t add up: Combatting sample bias. LREC, 2014 (acceptance rate ~60%).
    [Abstract]  [PDF]
  11. Yulia Tsvetkov, Nathan Schneider, Dirk Hovy, Archna Bhatia, Manaal Faruqui, and Chris Dyer: Augmenting English adjective senses with supersenses. LREC, 2014 (acceptance rate ~60%).
    [Abstract]  [PDF]
  12. Hege Fromreide, Dirk Hovy, and Anders Søgaard: Crowdsourcing and annotating NER for Twitter #drift. LREC, 2014 (acceptance rate ~60%).
    [Abstract]  [PDF]

2013

  1. Shashank Srivastava, Dirk Hovy: A Walk-based Semantically Enriched Tree Kernel Over Distributed Word Representations. EMNLP, 2013 (acceptance rate 27%).
    [Abstract]  [PDF]
  2. Dirk Hovy: Learning Semantic Types and Relations from Text. PhD Thesis, 2013.
    [Abstract]  [PDF]
  3. Dirk Hovy, Gopala Anumanchipalli, Alok Parlikar, Caroline Vaughn, Adam Lammert, Eduard Hovy and, Alan W Black: Analysis and Modeling of "Focus" in Context. Interspeech, 2013 (acceptance rate 52%).
    [Abstract]  [PDF]
  4. Dirk Hovy, Taylor Berg-Kirkpatrick, Ashish Vaswani, and Eduard Hovy: Learning Whom to Trust with MACE. NAACL HLT, 2013 (acceptance rate 30%).
    [Abstract]  [PDF]
  5. Mrinmaya Sachan, Dirk Hovy, and Eduard Hovy: Solving Electrical Networks to Incorporate Supervision in Random Walks. WWW Conference 2013, 2013 (acceptance rate 15%).
    [Abstract]  [PDF]
  6. Dirk Hovy, Shashank Srivastava, Sujay Kumar Jauhar, Mrinmaya Sachan, Kartik Goyal, Huying Li, Whitney Sanders, and Eduard Hovy: Identifying Metaphorical Word Use with Tree Kernels. NAACL HLT Meta4NLP Workshop, 2013.
    [Abstract]  [PDF]

2012

  1. Dirk Hovy and Eduard Hovy: Exploting Partial Annotations with EM Training. NAACL HLT Workshop on the Induction of Linguistic Structure (WILS), 2012.
    [Abstract]  [PDF]
  2. Dirk Hovy: Programming in Python for Linguists — A Gentle Introduction. Tutorial, 2012.
    [Abstract]  [PDF]
  3. Dirk Hovy, James Fan, Alfio Gliozzo, Siddharth Patwardhan, and Chris Welty: When Did that Happen? — Linking Events and Relations to Timestamps. EACL, 2012 (acceptance rate 26%).
    [Abstract]  [PDF]

2011

  1. Stephan Gouws, Dirk Hovy, and Donald Metzler: Unsupervised Mining of Lexical Variants from Noisy Text. EMNLP Workshop on Unsupervised Learning in NLP (UNSUP 2011), 2011.
    [Abstract]  [PDF]
  2. Dirk Hovy, Ashish Vaswani, Stephen Tratz, David Chiang, and Eduard Hovy: Models and Training for Unsupervised Preposition Sense Disambiguation. ACL HLT Short Papers, 2011 (acceptance rate 25%).
    [Abstract]  [PDF]
  3. Dirk Hovy, Chunliang Zheng, Eduard Hovy, and Anselmo Peñas: Unsupervised Discovery of Domain-Specific Knowledge from Text. ACL HLT, 2011 (acceptance rate 26%).
    [Abstract]  [PDF]

2010

  1. Dirk Hovy, Stephen Tratz, and Eduard Hovy: What’s in a Preposition? Dimensions of Sense Disambiguation for an Interesting Word Class. COLING, 2010 (acceptance rate 41%).
    [Abstract]  [PDF]
  2. Dirk Hovy: An Evening with… EM. Tutorial, 2010.
    [Abstract]  [PDF]

2009

  1. Stephen Tratz, Dirk Hovy: Disambiguation of Preposition Sense Using Linguistically Motivated Features. NAACL HLT, 2009 (acceptance rate 59%).
    [Abstract]  [PDF]

2007

  1. Dirk Hovy: Regionalität in historischen Texten. Handout of a talk at the University of Kassel., 2007.
    [Abstract]  [PDF]

2006

  1. Dirk Hovy: Sprachwandel in der Großstadtregion. Master thesis, 2006.
    [Abstract]  [PDF]

    Beware — large file!

2005

  1. Dirk Hovy: Phonologische Untersuchung zu Vornamen im Deutschen. Term paper, 2005.
    [Abstract]  [PDF]

2004

  1. Dirk Hovy: Hedges. Term paper, 2004.
    [Abstract]  [PDF]
  2. Dirk Hovy: Collocations or Free Variation? Empirical Study. Term paper, 2004.
    [Abstract]  [PDF]

Möchten Sie diese Website lieber auf deutsch lesen?

Valid XHTML 1.0 Transitional Valid CSS!