Thursday, January 13, 2011

Reading for 1/20/11: Kwiatkowski et al., 2010

Here is the first reading:

Inducing Probabilistic CCG Grammars from Logical Form with Higher-order Unification
Authors:  Tom Kwiatkowski, Luke Zettlemoyer, Sharon Goldwater, and Mark Steedman
Venue:  EMNLP 2010
Leader:  Weisi


  • Leave a comment on this post (non-anonymously) giving the details of the related paper you will read (include a URL), by Monday, January 17.
  • Post your commentary (a paragraph) as a new blog post, by Wednesday, January 19.
  • If you haven't received a message from the 11-713 mailing list listing the schedule for leading discussions, let Tae know.


  1. I think I plan to read this review of the CCG formalism.

    Mark Steedman and Jason Baldridge. Combinatory Categorial Grammar. To appear in Robert Borsley and Kersti Borjars (eds.) Constraint-based approaches to grammar: alternatives to transformational syntax. Oxford: Blackwell. PDF (Will appear in February 2011.)

    Mark Steedman's website claims a different citation "forthcoming 2007" for a differently titled book, but that book appears not to have ever existed.

  2. I plan to read the following paper in order to learn about one of the other methods for solving this problem.
    Lu et al. A generative model for parsing natural language to meaning representations. EMNLP 2008.

  3. I plan to read:

    Unsupervised Semantic Parsing
    Hoifung Poon, Pedro Domingos, EMNLP 2009

    Similar goal (mapping text to formal meaning representations), but different setting (unsupervised versus supervised).

  4. This comment has been removed by the author.

  5. I will read the following paper (by one of the co-authors):

    Zettlemoyer, L.S. & Collins, M.
    Learning context-dependent mappings from sentences to logical form

    The problem addressed now deals with context-dependent mappings.

  6. I plan to read the following paper -

    Clark, S. & Curran, J. R. (2007). Wide-coverage efficient
    statistical parsing with CCG and log-linear models.
    Computational Linguistics, 33(4), 493–552.

    It presents a set of log linear methods for parsing CCGs and develops a strategy to build a CCG parser.

    *This is a very lengthy paper (~60 pages), so I aim at reading a significant part.

  7. This comment has been removed by the author.

  8. This comment has been removed by the author.

  9. I plan to read the paper:

    Luke S. Zettlemoyer, Michael Collins. Learning Context-dependent Mappings from Sentences to Logical Form. In Proceedings of the Joint Conference of the Association for Computational Linguistics and International Joint Conference on Natural Language Processing (ACL-IJCNLP), 2009.

  10. I am going to read one of the discussed related papers:

    Yuk Wah Wong; Raymond Mooney
    Learning for Semantic Parsing with Statistical Machine Translation

    This work applies established techniques from the area of statistical machine translation to the task of semantic parsing.

  11. I pick the same paper as Michael:

    Yuk Wah Wong; Raymond Mooney
    Learning for Semantic Parsing with Statistical Machine Translation

    To be honest, I pick it because I'm interested in SMT techniques and want to see how they can relate to the topic discussed in our focus paper.

  12. "Using string-kernels for learning semantic parsers"


    With limited experience in semantic parsing, I selected this paper from the references of this week's primary paper. It learns a SVM classifier for each possible production in the semantic grammar. These are used to compose entire semantic derivations. The authors claim it is robust against "noise."

  13. I am planning to read:

    Bos, J., Clark, S., Steedman, M., Curran, J. R., & Hockenmaier, J. (2004). Wide-coverage semantic representations from a CCG parser. In Proceedings of the International Conference on Computational Linguistics

    Which looks like an interesting, earlier result using similar techniques.


Note: Only a member of this blog may post a comment.