Unifying Syntactic and Semantic Approaches to Unaccusativity: A Connectionist Approach

Legendre, Géraldine; Miyata, Yoshiro; Smolensky, Paul

doi:10.3765/bls.v17i0.1643

Cited by 11 publications

(7 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, we assume that acceptability judgment intuitions minimally reflect the well-formedness of syntactic derivations and semantic representations that the parser assigns to a given sentence. When this process fails due to linguistic or other cognitive constraints, we perceive degradation in sentence acceptability ( Schütze, 1996 ), and the severity of degradation reflects the number of constraint violations at all levels of representations ( Legendre et al, 1991 ; Keller, 2000 ; Smolensky and Legendre, 2006 ; Haegeman et al, 2014 ). Second, we also assume that syntactic constraints on wh -islands do play an important role in accounting for the general acceptability degradation due to extraction out of wh -islands, and this constraint could be the original Relativized Minimality constraint in Rizzi (1990 , 2004 ) which did not distinguish bare identity wh -island from inclusion wh -island.…”

Section: Discussionmentioning

confidence: 99%

Similarity of wh-Phrases and Acceptability Variation in wh-Islands

et al. 2016

View full text Add to dashboard Cite

In wh-questions that form a syntactic dependency between the fronted wh-phrase and its thematic position, acceptability is severely degraded when the dependency crosses another wh-phrase. It is well known that the acceptability degradation in wh-island violation ameliorates in certain contexts, but the source of this variation remains poorly understood. In the syntax literature, an influential theory – Featural Relativized Minimality – has argued that the wh-island effect is modulated exclusively by the distinctness of morpho-syntactic features in the two wh-phrases, but psycholinguistic theories of memory encoding and retrieval mechanisms predict that semantic properties of wh-phrases should also contribute to wh-island amelioration. We report four acceptability judgment experiments that systematically investigate the role of morpho-syntactic and semantic features in wh-island violations. The results indicate that the distribution of wh-island amelioration is best explained by an account that incorporates the distinctness of morpho-syntactic features as well as the semantic denotation of the wh-phrases. We argue that an integration of syntactic theories and perspectives from psycholinguistics can enrich our understanding of acceptability variation in wh-dependencies.

show abstract

Section: Discussionmentioning

confidence: 99%

Similarity of wh-Phrases and Acceptability Variation in wh-Islands

et al. 2016

View full text Add to dashboard Cite

show abstract

“…The first approach uses rewrite rules (Chomsky and Halle, 1968 ) or finite state automata (Heinz, 2010 ; Chandlee, 2014 ) to derive outputs from inputs through derivation. A connectionist approach called Optimality Theory (Prince and Smolensky, 2004 ) and related proposals such as Harmonic Grammar and Maximum Entropy (MaxEnt) grammar (Legendre et al, 1990 , 2006 ; Goldwater and Johnson, 2003 ; Wilson, 2006 ; Hayes and Wilson, 2008 ; Pater, 2009 ; Hayes and White, 2013 ; White, 2014 , 2017 ), on the other hand, model phonological grammar as input-output pairing: the grammar chooses the most optimal output given an input. These models were heavily influenced by the early advances in neural network research (Alderete and Tupper, 2018a ; Pater, 2019 ).…”

Section: Previous Workmentioning

confidence: 99%

Generative Adversarial Phonology: Modeling Unsupervised Phonetic and Phonological Learning With Neural Networks

Beguš

2020

Front. Artif. Intell.

109

View full text Add to dashboard Cite

Training deep neural networks on well-understood dependencies in speech data can provide new insights into how they learn internal representations. This paper argues that acquisition of speech can be modeled as a dependency between random space and generated speech data in the Generative Adversarial Network architecture and proposes a methodology to uncover the network's internal representations that correspond to phonetic and phonological properties. The Generative Adversarial architecture is uniquely appropriate for modeling phonetic and phonological learning because the network is trained on unannotated raw acoustic data and learning is unsupervised without any language-specific assumptions or pre-assumed levels of abstraction. A Generative Adversarial Network was trained on an allophonic distribution in English, in which voiceless stops surface as aspirated word-initially before stressed vowels, except if preceded by a sibilant [s]. The network successfully learns the allophonic alternation: the network's generated speech signal contains the conditional distribution of aspiration duration. The paper proposes a technique for establishing the network's internal representations that identifies latent variables that correspond to, for example, presence of [s] and its spectral properties. By manipulating these variables, we actively control the presence of [s] and its frication amplitude in the generated outputs. This suggests that the network learns to use latent variables as an approximation of phonetic and phonological representations. Crucially, we observe that the dependencies learned in training extend beyond the training interval, which allows for additional exploration of learning representations. The paper also discusses how the network's architecture and innovative outputs resemble and differ from linguistic behavior in language acquisition, speech disorders, and speech errors, and how well-understood dependencies in speech data can help us interpret how neural networks learn their representations.

show abstract

“…Harmonic Grammar (Legendre, Miyata, & Smolensky, 1990a, 1990b, 1991Smolensky et al, 1992;Smolensky, Legendre, & Miyata, 1993) is predecessor of OT that builds on the assumption that constraints are annotated with numeric weights (instead of just being rank-ordered as in Standard OT). Harmonic Grammar (HG) can be implemented in a hybrid connectionist-symbolic architecture and has been applied successfully to gradient data by Legendre et al (1990aLegendre et al ( , 1990b.…”

Section: Harmonic Grammarmentioning

confidence: 99%

Linear Optimality Theory as a Model of Gradience in Grammar

Keller¹

2006

Gradience in Grammar

129

View full text Add to dashboard Cite

This paper provides an overview of Linear Optimality Theory (LOT), a variant of Optimality Theory (OT) designed for the modeling of gradient acceptability judgment data. We summarize the empirical properties of gradient data that have been reported in the experimental literature, and use them to motivate the design of LOT. We discuss LOT's notions of constraint competition and optimality, as well as a new formulation of ranking argumentation, which makes it possible to apply standard parameter estimation techniques to LOT. Then the LOT model is compared to Standard OT, to Harmonic Grammar, and to recently proposed probabilisitic versions of OT.

show abstract

Unifying Syntactic and Semantic Approaches to Unaccusativity: A Connectionist Approach

Abstract: Proceedings of the Seventeenth Annual Meeting of the Berkeley Linguistics Society: General Session and Parasession on The Grammar of Event Structure (1991), pp. 156-167

Cited by 11 publications

References 0 publications

Similarity of wh-Phrases and Acceptability Variation in wh-Islands

Similarity of wh-Phrases and Acceptability Variation in wh-Islands

Generative Adversarial Phonology: Modeling Unsupervised Phonetic and Phonological Learning With Neural Networks

Linear Optimality Theory as a Model of Gradience in Grammar

Contact Info

Product

Resources

About