Natural Language Processing With Modular PDP Networks and Distributed Lexicon

By Risto Miikkulainen, Michael G. Dyer. 1991

How researchers see this paper

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

In Natural Language Processing

Citations in the corpus

BLOOM: A 176B-Parameter Open-Access Multilingual Language Model (2022, methodology): “Neural Language Models An alternative to n-gram models, first proposed by Miikkulainen and Dyer (1991) and Schmidhuber and Heil (1996) and later popularized by Bengio et al. (2000), is to use a neural network to estimate the probability of the next token given prior tokens.”
Modular Neural Networks and Self-Decomposition (1997, methodology): “The last example (see (Miikkulainen and Dyer 1991)) consists inusing a Kohonen algorithm to cluster the input space and then to apply locallya NN.Finally a di erent approach that can be also seen as a clustering of theinput space is embedded in Weight Sharing Networks or Time Delay NeuralNetworks…”
Artificial Life (2019, background): “In fact, fitness is achieved through innovation in engineering of the organism [81].”
Structure and deterioration of semantic memory: a neuropsychological and computational investigation. (2004, background): “The capacity of connectionist networks to acquire abstract, distributed concept representations has been explored by several researchers (Elman, 1990; Hinton, 1986; Miikkulainen & Dyer, 1991; Rumelhart & Todd, 1993; Schyns, 1991), but this work has tended to be somewhat too abstract to provide a b”
Learning Deep Architectures for AI (2007, background): “The idea of distributed representation is an old idea in machine learning and neural networks research [15, 68, 128, 157, 170], and it may be of help in dealing with”
A Neural Syntactic Language Model (2005, unknown): “The idea of using neural networks for natural language processing has been also studied earlier (e.g. Miikkulainen & Dyer, 1991).”
Dyslexic and category-specific aphasic impairments in a self-organizing feature map model of the lexicon. (1997, methodology): “With the FGREP-mechanism (Miikkulainen, 1993; Miikkulainen & Dyer, 1991), it is possible to derive a distributed encoding automatically, based on examples of how the words are used in the language.”
A Neural Probabilistic Language Model (2003, methodology): “[ 8 ]. In contrast, here we push this idea to a large scale, an d concentrate on learning a statistical model of the distribution of word sequences, rath er than learning the role of words in a sentence.”
Neural Probabilistic Language Models (2006, methodology): “The idea of using neural networks for language modeling is not new either, e.g. [ Miikkulainen and Dyer, 1991 ].”
Continuous space language models (2007, background): “Another approach to connectionist natural language processing, based on hierarchically organized modular subnetworks and a central lexicon, was developed by Miikkulainen and Dyer (1991).”