Learn more by training less: systematicity in sentence processing by recurrent networks
By Stefan L. Frank. 2006
36 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Representation & Self-Supervised Learning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Douwe Kiela
- Mohit Bansal
- Luke S. Zettlemoyer
- Felix Hill
- John Wieting
- Andrew Kyle Lampinen
- Graham Neubig
- Yoshua Bengio
In Representation & Self-Supervised Learning
- John Wieting
- Douwe Kiela
- Matthew Botvinick
- Adam Santoro
- Andrew Kyle Lampinen
- Felix Hill
- Peter Alexander Jansen
- Scott Watter
Citations in the corpus
- Environmental drivers of systematicity and generalization in a situated agent (2019, background): “, 2018), and are more aligned with older empirical analyses of neural networks (McClelland et al., 1987; Frank, 2006).”
- Emergent Systematic Generalization in a Situated Agent (2019, result): “With respect to generalization, systematicity and neural networks, our findings contrast with other recent contributions (Lake, 2019; Bahdanau et al., 2018), and are more aligned with older empirical analyses of neural networks (McClelland et al., 1987; Frank, 2006).”
- No Training Required: Exploring Random Encoders for Sentence Classification (2019, background): “(Frank, 2006a;b) investigated whether ESNs are capable of displaying the systematicity in natural language.”
- A nice surprise? Predictive processing and the active pursuit of novelty (2018, background): “2 The use of multi-layer neural nets, engaged in a prediction task, to acquire approximations to grammatical knowledge in simplified domains is well established (Elman 1991, 1993; Frank (2006)).”
- Strong systematicity through sensorimotor conceptual grounding: an unsupervised, developmental approach to connectionist sentence processing (2012, methodology): “Frank (2006) argued that GPE, a measure of grammatical prediction performance, is a poor measure of grammatical systematicity in that it lacks a baseline measure, as a given transition may be more or less difficult than another, requiring differing depths of temporal look-back (and the systematic…”