Context-sensitive coding, associative memory, and serial order in (speech) behavior.

By Wayne A. Wickelgran. 1969

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Linguistics

Citations in the corpus

Deep Structured Output Learning for Unconstrained Text Recognition (2014, methodology): “ams in the language. For example, G 3(spires) = fs;p;i;r;e;s;sp;pi;ir;re;es;spi;pir;ire;resg. This method of encoding variable length sequences is similar to the Wickelphone phoneme-encoding methods (Wickelgran (1969)). Even for small values of N, G N(w) encodes each word w2Wnearly uniquely. For exa”
RNNs Implicitly Implement Tensor Product Representations (2018, unknown): “Wickelroles: Each digit’s role is the digit before it and the digit after it (Wickelgren, 1969).”
Understanding normal and impaired word reading: computational principles in quasi-regular domains. (1996, background): “This approach, which originated with Wickelgren (1969), makes the representation of each element context sensitive without being rigidly tied to position.”
Generalizable Relational Binding from Coarse-coded Distributed Representations (2001, methodology): “A similar demonstration was recently provided by Mel and Fiser (2000) in an analysis of distributed, low-order conjunctive representations (resembling “Wickelfeatures”; Wickelgren, 1969; Seidenberg & McClelland, 1989) in the domain of textual inputs.”
On language and connectionism: analysis of a parallel distributed processing model of language acquisition (1988, background): “To overcome this, Rumelhart and McClelland turn to a scheme proposed by Wickelgren (1969), according to which a string is represented as the set of the trigrams (3-character-sequences) that it contains.”
Serial Order: A Parallel Distributed Processing Approach (1997, background): “First, it requires a large number of elements, yet has difficulty with the pronunciation of words, such as barnyard, that have repeated subsequences of length two or more (Wickelgren, 1969).”