Four Problems with Extracting Human Semantics from Large Text Corpora

@misc{french02four, abstract = {We present four problems that will have to be overcome by text co-occurrence programs in order for them to be able to capture human-like semantics. These problems are: the intrinsic deformability of semantic space, the inability to detect co-occurrences of (esp. distal) abstract structures, their lack of essential world knowledge, which humans acquire through learning or direct experience with the world and their assumption of the atomic nature of words. By looking at a number of very...}, author = {French, Robert M. and Labiouse, Christophe }, booktitle = {Proceedings of the 24th Annual Conference of the Cognitive Science Society}, citeulike-article-id = {478649}, keywords = {latent-semantic-analysis}, posted-at = {2006-01-24 03:45:04}, priority = {4}, title = {Four Problems with Extracting Human Semantics from Large Text Corpora}, url = {http://citeseer.ist.psu.edu/546518.html}, year = {2002} }

TY - GEN ID - french02four L3 - citeulike-article-id:478649 TI - Four Problems with Extracting Human Semantics from Large Text Corpora T2 - Proceedings of the 24th Annual Conference of the Cognitive Science Society N2 - We present four problems that will have to be overcome by text co-occurrence programs in order for them to be able to capture human-like semantics. These problems are: the intrinsic deformability of semantic space, the inability to detect co-occurrences of (esp. distal) abstract structures, their lack of essential world knowledge, which humans acquire through learning or direct experience with the world and their assumption of the atomic nature of words. By looking at a number of very... KW - latent-semantic-analysis AU - French, Robert AU - Labiouse, Christophe PY - 2002/// UR - http://citeseer.ist.psu.edu/546518.html ER -