On Aspects of the Theory of Syntax
By A. D. Di Sciullo. 2021
2,371 citations recorded by the source corpus.
In the first essay for a new series on landmark texts, Anna Maria Di Sciullo revisits Noam Chomsky’s classic Aspects on the Theory of Syntax. Published in 1965, Aspects was a revelation, presenting linguists with what, at once, became the Standard Theory. It promoted linguistics into a science, one that accepted the methods and the standards of the hard sciences themselves.
Subfields: Language and Linguistics, Linguistics
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Language and Linguistics
- Yoav Goldberg
- Nicolás Navarro-Guerrero
- Anabel Martín-González
- Antonio Torralba
- Noah A. Smith
- Anna Rogers
- Nathan Scales
- Olivier Bousquet
In Linguistics
- Nicolás Navarro-Guerrero
- Anabel Martín-González
- Antonio Torralba
- Noah A. Smith
- Anna Rogers
- Yejin Choi
- Stefan Wermter
- Yossi Matias
Citations in the corpus
- Neural Network Acceptability Judgments (2018, neutral): “The influential argument from the poverty of the stimulus (APS) holds that the extent of human linguistic competence cannot be explained by purely domain general learning mechanisms and that humans must be born with a Universal Grammar which imparts specific knowledge of grammatical universals to th”
- CommonGen: A Constrained Text Generation Challenge for Generative Commonsense Reasoning (2020, background): “This compositionally generalization ability via analogy, i.e., to make “infinite use of finite means” (Chomsky, 1965), is challenging for machines.”
- Measuring Compositional Generalization: A Comprehensive Method on Realistic Data (2019, background): “Human intelligence exhibits systematic compositionality (Fodor & Pylyshyn, 1988), the capacity to understand and produce a potentially infinite number of novel combinations of known components, i.e., to make “infinite use of finite means” (Chomsky, 1965).”
- Probing Natural Language Inference Models through Semantic Fragments (2019, methodology): “In contrast to work on empirical NLI, such linguistic work often emphasizes the complex cases of each phenomena in order measure competence (see Chomsky (1965) for a discussion about competence vs. performance). For our fragments that test basic logic, the target formal system includes basic boolean”
- Changing the World by Changing the Data (2021, background): “A key part of that change is the linguistic signals we encounter in communication: on the nativist account children have innate constraints that guide7 their learning from the data they encounter (Chomsky, 2014; Hornstein and Lightfoot, 1985), and on the usage-based accounts (Bybee, 2006; Lieven and”
- Compositional Visual Generation with Composable Diffusion Models (2022, background): “We are able to make ‘infinite use of finite means’ [4], i.”
- Grounded PCFG Induction with Images (2020, background): “…raw text only (Jin et al., 2018b, 2019; Kim et al., 2019b,a; Drozdov et al., 2019), providing evidence against the poverty of the stimulus argument (Chomsky, 1965), and showing that many linguistic distinctions like lexical and phrasal categories can be directly induced from raw text statistics.”
- Composer: Creative and Controllable Image Synthesis with Composable Conditions (2023, background): “– Noam Chomsky (Chomsky, 1965) Generative image models conditioned on text can now produce photorealistic and diverse images (Ramesh et al., 1 Alibaba Group 2 Ant Group.”
- Provable Limitations of Acquiring Meaning from Ungrounded Form: What Will Future Language Models Understand? (2021, background): “Competence vs. Performance Chomsky (1965) differentiates competence and performance in linguistic theory, where competence corresponds roughly to the correct algorithmic modeling of a linguistic process, and performance describes its implementation subject to resource constraints like memory.”
- Understanding heritage languages (2019, neutral): “(Rothman, 2009: 156) As with all definitions meant to neatly characterize a heterogeneous group of individuals, this one is an idealization, as is the idealized monolingual (e.g., Chomsky, 1965) or the truly balanced bilingual (Grosjean, 2010).”
- Statistical learning: From acquiring specific items to forming general rules (2012, positive): “…, out of many that are possible—and has suggested that language learners will fail to acquire languages that do not exhibit these regularities (Chomsky, 1965, 1995; Croft, in Syllable B Syllable A le wi ji de di je li we wiwidi wiwije wiwi li wiwiwe ji ji di ji ji je ji ji li ji ji we…”
- Survey on reinforcement learning for language processing (2021, methodology): “Through the years, NLP research has gone from being heavily influenced by theories of linguistics, such as those proposed by Noam Chomsky [16, 17], to the corpus linguistics approach of machine learning algorithms”