Change search
ReferencesLink to record
Permanent link

Direct link
Permutations as a means to encode order in word space
Number of Authors: 3
2008 (English)Conference paper (Refereed)
Abstract [en]

We show that sequence information can be encoded into high-dimensional fixed-width vectors using permutations of coordinates. Computational models of language often represent words with high-dimensional semantic vectors compiled from word-use statistics. A word's semantic vector usually encodes the contexts in which the word appears in a large body of text but ignores word order. However, word order often signals a word's grammatical role in a sentence and thus tells of the word's meaning. Jones and Mewhort (2007) show that word order can be included in the semantic vectors using holographic reduced representation and convolution. We show here that the order information can be captured also by permuting of vector coordinates, thus providing a general and computationally light alternative to convolution.

Place, publisher, year, edition, pages
2008, 1.
National Category
Computer and Information Science
URN: urn:nbn:se:ri:diva-22913OAI: diva2:1042478
The 30th Annual Meeting of the Cognitive Science Society (CogSci'08)
Available from: 2016-10-31 Created: 2016-10-31

Open Access in DiVA

fulltext(101 kB)1 downloads
File information
File name FULLTEXT01.pdfFile size 101 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Computer and Information Science

Search outside of DiVA

GoogleGoogle Scholar
Total: 1 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 4 hits
ReferencesLink to record
Permanent link

Direct link