Running Head Word Association Spaces 1 Word Association Spaces Semantic Spaces based on Free Association that Predict Memory Performance Send correspondence to
and the result is a high dimensional space in which words that appear in similar contexts are
placed in similar regions of the space. Landauer and Dumais (1997) applied the LSA approach to
over 60,000 words appearing in over 30,000 contexts of a large encyclopedia. More recently,
LSA was applied to over 90,000 words appearing in over 37,000 contexts of reading material
that an English reader might be exposed to from 3rd grade up to 1st year of college from various
sources such as textbooks, novels, and newspaper articles. The SVD method placed these words
in a high dimensional space with the number of dimensions chosen between 200 and 400. The
LSA representation has been successfully applied to multiple choice vocabulary tests, domain
knowledge tests and content evaluation (see Landauer & Dumais, 1997; Landauer et al. 1998).
Another framework that has been used to place words in a high dimensional semantic
space is the Hyperspace Analogue to Language (Burgess, Livesay, & Lund, 1998; Lund &
Burgess, 1996; see Burgess & Lund, 2000 for an overview). The HAL model develops high
dimensional vector representations for words based on a co-occurrence analysis of large samples
of written text. For 70,000 words, the co-occurrence statistics were calculated in a 10 word
window that was slid over the text from a corpus of over 320 million words (gathered from
Usenet newsgroups). For each word, the co-occurrence statistics were calculated for the 70,000
words appearing before and after that word in the 10 word window. The resulting 140,000 values
for each word were the feature values for the words in the HAL representation. Because the
representation is based on the context in which words appear, the HAL vector representation is
also referred to as a contextual space: words that appear in similar contexts are represented by
similar vectors. The HAL and LSA approach are similar in one major assumption: similar words
occur in similar contexts. In both HAL and LSA, the placement of words in a high dimensional
semantic space is based on an analysis of the co-occurrence statistics of words in their contexts.
热门文档