Project Overview
The S-Space Package is a collection of algorithms for building Semantic Spaces. These algorithms process text corpora and map semantic representations for words onto high dimensional vectors. These approaches are known by many names, such as word spaces, semantic spaces, or distributed semantics.
The research and development is being done by the Natural Language Processing group at UCLA led by David Jurgens and Keith Stevens, under the advisory of Dr. Michael Dyer.
See the Getting Started page for a quick introduction on how to use the S-Space package, or see the Package Overview for information on the code and available features.
Goal
Our initial goal is to provide a uniform implementation for many common semantic space algorithms in order to facilitate research in semantic spaces and provide an accurate, reproducible way to compare different algorithms.
Second, we aim to provide a comprehensive framework for researchers to easily develop new algorithms without having to replicate much of the shared software.
For those looking to implement their own Semantic Space algorithm within the S-Space package, we recommend looking at the Introduction page.
Contact
Questions and Comments can be sent to s-space-research-dev@googlegroups.com
Algorithms
We are actively working on supporting the following algorithms. As additional time and resources allow, we will add further algorithms. See the downloads page for the current list of algorithms available in command-line executable form.
Latent Semantic Analysis (LSA)
T. K. Landauer and S. T. Dumais, "A solution to Plato’s problem: The Latent Semantic Analysis theory of the acquisition, induction, and representation of knowledge," Psychological Review, vol. 104, pp. 211–240, 1997.
T. K. Landauer, P. W. Foltz, and D. Laham, "Introduction to Latent Semantic Analysis," Discourse Processes, no. 25, pp. 259–284, 1998.
Random Indexing (also, with permutations)
P. Kanerva, J. Kristoferson, and A. Holst, “Random indexing of text samples for latent semantic analysis,” in Proceedings of the 22nd Annual Conference of the Cognitive Science Society, L. R. Gleitman and A. K. Josh, Eds., 2000, p. 1036.
M. Sahlgren, “Vector-based semantic analysis: Representing word meanings based on random labels,” in Proceedings of the ESSLLI 2001 Workshop on Semantic Knowledge Acquisition and Categorisation, Helsinki, Finland, 2001.
M. Sahlgren, A. Holst, and P. Kanerva, “Permutations as a means to encode order in word space,” in Proceedings of the 30th Annual Meeting of the Cognitive Science Society (CogSci’08), 2008.
Correlated Occurrence Analogue to Lexical Semantic (COALS)
D. L. T. Rohde, L. M. Gonnerman, and D. C. Plaut, “An improved model of semantic similarity based on lexical co-occurrence,” Cognitive Science, 2009, submitted. Online. Available: http://www.cnbc.cmu.edu/plaut/papers/abstracts/RohdeGonnermanPlautSUB-CogSci.COALS.html
Hyperspace Analogue to Language (HAL)
C. Burgess and P. Conley, “Developing semantic representations for proper names,” in Cognitive Science Proceedings, LEA, 1998, pp. 185–190.
C. Burgess and K. Lund, “Modelling parsing constraints with high- dimensional context space,” Language and Cognitive Processes, vol. 12, pp. 177–210, 1997.
Latent Relational Analysis (LRA)
P. D. Turney, “Similarity of semantic relations,” Computational Linguistics, vol. 32, no. 3, pp. 379–416, 2006.
Bound Encoding of the Aggregate Language Environment (BEAGLE)
M. N. Jones, W. Kintsch, and D. J. K. Mewhort, “High-dimensional semantic space accounts of priming,” Journal of Memory and Language, vol. 55, pp. 534–552, 2006.
M. N. Jones and D. J. K. Mewhort, “Representing word meaning and order information in a composite holographic lexicon,” Psychology Review, vol. 114, pp. 1–37, 2007.
Syntactic Co-occurrence (by Greffenstette)
G. Grefenstette, Explorations in Automatic Thesaurus Discovery. Indiana University Press, 1994.
License and Restrictions
The S-Space software package is free software released under the GPL v. 2 license. See our license and restrictions page for full details.
