Suresh Manandhar’s Home Page

BibTex

@InProceedings{reddy-EtAl:2011:IJCNLP-2011,
  author    = {Reddy, Siva  and  Klapaftis, Ioannis  and  McCarthy, Diana  and  Manandhar, Suresh},
  title     = {Dynamic and Static Prototype Vectors for Semantic Composition},
  booktitle = {Proceedings of 5th International Joint Conference on Natural Language Processing (IJCNLP-2011)},
  month     = {November},
  year      = {2011},
  address   = {Chiang Mai, Thailand,[Best Paper Award] },
  publisher = {Asian Federation of Natural Language Processing},
  pages     = {705--713 },
  url= {http://www.aclweb.org/anthology/I/I11/I11-1079.pdf}
  abstract = {Compositional Distributional Semantic
methods model the distributional behavior
of a compound word by exploiting the
distributional behavior of its constituent
words. In this setting, a constituent word
is typically represented by a feature vector
conflating all the senses of that word.
However, not all the senses of a constituent
word are relevant when composing the semantics
of the compound. In this paper,
we present two different methods for selecting
the relevant senses of constituent
words. The first one is based on Word
Sense Induction and creates a static multi
prototype vectors representing the senses
of a constituent word. The second creates
a single dynamic prototype vector for each
constituent word based on the distributional
properties of the other constituents
in the compound. We use these prototype
vectors for composing the semantics
of noun-noun compounds and evaluate
on a compositionality-based similarity
task. Our results show that: (1) selecting
relevant senses of the constituent
words leads to a better semantic composition
of the compound, and (2) dynamic
prototypes perform better than static prototypes. 
Presentation:http://www.cs.york.ac.uk/aig/nl/datasets/compositionalityDataset/DynPrp.pdf}
}