Learnability and the Statistical Structure of Language: Poverty of Stimulus Arguments Revisited

By John D. Lewis, Jeffrey L. Elman. 2004

120 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/ab4c1da6b9ecfa12d31b3767abb758726be92583

How researchers see this paper

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

Citations in the corpus

Can neural networks acquire a structural bias from raw linguistic data? (2020, background): “There have been several prior efforts to test neural networks for a structural bias in the domain of subject-auxiliary inversion (Lewis & Elman, 2001; Frank & Mathis, 2007; McCoy et al., 2018, 2020).”
The Acquisition of Anaphora by Simple Recurrent Networks (2013, background): “Indeed, this is what Lewis & Elman (2001) found in their study of subject-auxiliary inversion, where the network apparently generalized its knowledge of inversion to withheld constructions.”
Is neural language acquisition similar to natural? A chronological probing study (2022, background): “Thus, (Lewis and Elman, 2001) train a simple RNN to discriminate between grammatical strings that follow the inversion rule and those that do not (e.g., moving the ﬁrst auxiliary verb such as “Is the man that tall is nice?”).”
Connectionist Models in Developmental Cognitive Neuroscience : Critical Periods and the Paradox of Success (2005, background): “…grammatical knowledge (e.g., the lack of explicit negative evidence, the lack of consistent feedback about grammaticality) are moot if the acquisition task is reformulated as acquiring the neural networks that support comprehension and production (Seidenberg, 1997, 2003; Lewis & Elman, 2001).”
Revisiting the poverty of the stimulus: hierarchical generalization without a hierarchical bias in recurrent neural networks (2018, background): “Lewis and Elman (2001) argued that an RNN trained to predict the next word can learn which questions are well formed, but this conclusion was convincingly called into question by Kam, Stoyneshka, Torny-ova, Fodor, and Sakas (2008).”
Unraveling the Dyad: Using Recurrence Analysis to Explore Patterns of Syntactic Coordination Between Children and Caregivers in Conversation (2006, background): “Accompanying this is the growing evidence that positive statistical information available in the input is sufficient to drive considerable generalization for learning grammatical structure (e.g., Lewis & Elman, 2001; Mintz, 2003; Reali & Christiansen, 2003).”
Poverty of the Stimulus? A Rational Approach (2006, methodology): “For instance, the models used by Reali and Christiansen (2004) and Lewis and Elman (2001) measure success by whether they predict the next word in a sequence, rather than based on examination of an explicit grammar.”
Variability and Variation in Second Language Acquisition Orders: A Dynamic Reevaluation (2015, background): “However, more and more researchers in this ﬁeld are starting to realize that an innate system is not only a redundant assumption to account for language development (Lewis & Elman, 2002; O’Grady, 2015), but also that language emerges from continuous interactions on all time scales.”