Experimental Support for a Categorical Compositional Distributional Model of Meaning

Computer Science – Computation and Language

Scientific paper

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

11 pages, to be presented at EMNLP 2011, to be published in Proceedings of the 2011 Conference on Empirical Methods in Natural

Scientific paper

Modelling compositional meaning for sentences using empirical distributional methods has been a challenge for computational linguists. We implement the abstract categorical model of Coecke et al. (arXiv:1003.4394v1 [cs.CL]) using data from the BNC and evaluate it. The implementation is based on unsupervised learning of matrices for relational words and applying them to the vectors of their arguments. The evaluation is based on the word disambiguation task developed by Mitchell and Lapata (2008) for intransitive sentences, and on a similar new experiment designed for transitive sentences. Our model matches the results of its competitors in the first experiment, and betters them in the second. The general improvement in results with increase in syntactic complexity showcases the compositional power of our model.

No associations

LandOfFree

Say what you really think

Search LandOfFree.com for scientists and scientific papers. Rate them and share your experience with other people.

Rating

Experimental Support for a Categorical Compositional Distributional Model of Meaning does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Experimental Support for a Categorical Compositional Distributional Model of Meaning, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Experimental Support for a Categorical Compositional Distributional Model of Meaning will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFWR-SCP-O-177468

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.