I'm a Ph.D student at Stanford (since 2010) advised by Chris Manning, in the natural language processing group. I graduated from The University of California (Berkeley) in 2010 with a B.S. in Electrical Engineering / Computer Science.

My interests are in natural language understanding Particularly, I am interested in interpreting spatial and temporal expressions and, more broadly, in finding grounded meaning in natural language. Recently, I have also been thinking about generalizing knowledge stored in open-domain sources such as WordNet, ReVerb, or ConceptNet.

In my free time, I enjoy the outdoors (hiking / camping / backpacking), board games, and movies.

• 2012
• Parsing Time: Learning to Interpret Time Expressions
  Gabor Angeli, Chris Manning, Dan Jurafsky,
  North American Chapter of the Association for Computational Linguistics (NAACL). 2012

  We present a probabilistic approach for learning to interpret temporal phrases given only a corpus of utterances and the times they reference. While most approaches to the task have used regular expressions and similar linear pattern interpretation rules, the possibility of phrasal embedding and modification in time expressions motivates our use of a compositional grammar of time expressions. This grammar is used to construct a latent parse which evaluates to the time the phrase would represent, as a logical parse might evaluate to a concrete entity. In this way, we can employ a loosely supervised EM-style bootstrapping approach to learn these latent parses while capturing both syntactic uncertainty and pragmatic ambiguity in a probabilistic framework. We achieve an accuracy of 72% on an adapted TempEval-2 task -- comparable to state of the art systems.

   @inproceedings{2012angeli-temporal,
    title = {Parsing Time: Learning to Interpret Time Expressions},
    author = {Gabor Angeli and Christopher D. Manning and Daniel Jurafsky},
    booktitle = {NAACL-HLT},
    year = {2012}
  }

  • Parsing Time, the main codebase
  Some of more reusable code (CKY, EM) lives here
  • The code makes heavy use of Stanford CoreNLP
  • The code is written in Scala 2.9.1

  [abstract] [bibtex] [code] [paper] [slides]
• 2010
• A Simple Domain-Independent Approach To Generation
  Gabor Angeli, Percy Liang, Dan Klein
  Empirical Methods in Natural Language Processing (EMNLP), 2010

  We present a simple, robust generation system which performs content selection and surface realization in a unified, domain-independent framework. In our approach, we break up the end-to-end generation process into a sequence of local decisions, arranged hierarchically and each trained discriminatively. We deployed our system in three different domains---Robocup sportscasting, technical weather forecasts, and common weather forecasts, obtaining results comparable to state-of-the-art domain-specific systems both in terms of BLEU scores and human evaluation.

   @inproceedings{2010angeli-generation,
    title = {A Simple Domain-Independent Probabilistic Approach to Generation},
    author = {Gabor Angeli and Percy Liang and Dan Klein},
    booktitle = {Empirical Methods in Natural Language Processing (EMNLP)},
    year = {2010}
  }

  • Sumtime Prodigy-METEO (Belz 2008) [homepage] [direct link]
  • Robocup (Chen and Mooney 2008) [homepage] [direct link]
  • WeatherGov (Liang et al. 2009) [homepage] [direct link]

  [abstract] [bibtex] [datasets] [paper] [slides]
• Miscellaneous
• Creation and Control of an Internet Controlled Mars Rover Model
  Gabor Angeli, Connie Walker
  American Astronomical Society (AAS), 2008
• Extraction and Analysis of Fresh Ginger Root and Ginger Dietary Supplement
  Gabor Angeli, Veronica Rodriguez Aniko Solyom
  118th AOAC Annual Meeting and Exposition, 2004

• I work in the Stanford NLP group
• I like to code in Scala and sometimes Ruby
• I often make slides and figures in rfig