Frege in Space: A Program of Compositional Distributional Semantics by Marco Baroni, Raffaela Bernardi, Roberto Zamparelli.
Abstract:
The lexicon of any natural language encodes a huge number of distinct word meanings. Just to understand this article, you will need to know what thousands of words mean. The space of possible sentential meanings is infinite: In this article alone, you will encounter many sentences that express ideas you have never heard before, we hope. Statistical semantics has addressed the issue of the vastness of word meaning by proposing methods to harvest meaning automatically from large collections of text (corpora). Formal semantics in the Fregean tradition has developed methods to account for the infinity of sentential meaning based on the crucial insight of compositionality, the idea that meaning of sentences is built incrementally by combining the meanings of their constituents. This article sketches a new approach to semantics that brings together ideas from statistical and formal semantics to account, in parallel, for the richness of lexical meaning and the combinatorial power of sentential semantics. We adopt, in particular, the idea that word meaning can be approximated by the patterns of co-occurrence of words in corpora from statistical semantics, and the idea that compositionality can be captured in terms of a syntax-driven calculus of function application from formal semantics.
At one hundred and ten (110) pages this is going to take a while to read and even longer to digest. What I have read so far is both informative and surprisingly, for the subject area, quite pleasant reading.
Thoughts about building up a subject identification by composition?
Enjoy!
I first saw this in a tweet by Stefano Bertolo.
This is very interesting. It reminds me of an article I recently read about a recent federal agency putting out a solicitation for a social media monitoring system which one of the requirements was the ability to detect sarcasm. This method seems like it could be applicable for something like that.
here is a link to the article
http://www.channel4.com/news/wanted-a-us-state-sponsored-sarcasm-detector
BTW the Captcha’s to leave a comment are brutal!
Comment by zbelcher@vizuri.com — July 2, 2014 @ 10:44 am
That’s a great story on detecting sarcasm. Thanks!
Yes, the Captcha’s are brutal but even so I get 30+ spam messages every day. I do full moderation so even if spam beats the Captcha’s, they won’t bother readers.
Comment by Patrick Durusau — July 8, 2014 @ 6:54 am