Three models for the description of language

By Noam Chomsky. 1956

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

Neural Turing Machines (2014, background): “Historically, cognitive science and linguistics emerged as ﬁelds at roughly the same time as artiﬁcial intelligence, all deeply inﬂuenced by the advent of the computer (Chomsky, 1956) (Miller, 2003).”
Natural Language Processing (Almost) from Scratch (2011, background): “ation. At rst glance, the ranking task appears unrelated to the induction of probabilistic grammars that underly standard parsing algorithms. The lack of hierarchical representation seems a fatal aw (Chomsky, 1956). However, ranking is closely related to an alternative description of the language st”
Visualisation and 'diagnostic classifiers' reveal how recurrent and recursive neural networks process hierarchical structure (2017, neutral): “Such hierarchical structures can be well represented by symbolic models (most famously, Chomsky, 1956; Montague, 1970), but if and how they can be represented by (artiﬁcial) neural models is an open question.”
TextWorld: A Learning Environment for Text-based Games (2018, methodology): “The engine generates object names, room descriptions, and quest instructions in constrained natural language using a context-free grammar (CFG) [Chomsky, 1956].”
Automatically Solving Number Word Problems by Semantic Parsing and Reasoning (2015, methodology): “Our parsing algorithm is based on context-free grammar (CFG) (Chomsky, 1956; Backus, 1959; Jurafsky & Martin, 2000), a commonly used mathematical system for modeling constituent structure in natural languages.”
Boosting Search Engines with Interactive Agents (2021, positive): “We take inspiration from generative, speciﬁcally context-free, grammars (CFGs) (Chomsky, 1956) and encode the structured action space as a set of production rules, which will be selected in (ﬁxed) top-down, left-to-right order.”
Frequency Effects on Syntactic Rule Learning in Transformers (2021, background): “…classes of stimuli: (1) natural sentences, which are generally both syntactically and semantically coherent, and (2) nonce sentences (following Gulordava et al. 2018) which are grammatically valid but not necessarily semantically coherent (“ colorless green ideas sleep furiously ”, Chomsky, 1956).”
SEScore2: Retrieval Augmented Pretraining for Text Generation Evaluation (2022, background): “However, as shown in Figure 1, in-batch text transformations mostly produce the negative samples that are syntactically, semantically incorrect (Chomsky, 1956) or both.”
Natural language based financial forecasting: a survey (2017, background): “Aligned with this tradition, the early popular approaches of NLP research as well take a view that emphasizes either the expressiveness [109] or language rules [30].”
A Usage-Based Approach to Recursion in Sentence Processing (2009, background): “This may due to the fact that even finite-state devices with bounded memory are able to process right-and leftbranching recursive structures of infinite length (Chomsky, 1956).”
Intuitive theories as grammars for causal inference (2007, background): “There is a long history of analogies between linguistic grammars and scientific theories, dating back at least to Chomsky’s early work on generative grammar in language (Chomsky, 1956; 1962).”