Learning OT constraint rankings using a maximum entropy model

By Sharon Goldwater, Mark Johnson. 2003

445 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/37f5b4fcb9d3631c34afe08c8adc748d512e1b1c

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

Locality and globality in phonological variation (2011, methodology): “(2)Models of variation based in Harmonic Grammar, such as Noisy HG (Boersma and Pater, 2008) or MaxEnt (Goldwater and Johnson, 2003) are also compatible with the proposal presented here.”
The Role of Phonetic Knowledge in Phonological Patterning: Corpus and Survey Evidence from Tagalog Infixation (2007, methodology): “A full explication of this framework is beyond the scope of this paper; see Goldwater & Johnson 2003 on applying Maximum Entropy to OT-like constraint weighting.”
Learning Phonology With Substantive Bias: An Experimental and Computational Study of Velar Palatalization (2006, unknown): “(6) (Goldwater & Johnson, 2003; Lafferty et al., 2001; McCallum, 2003), which assumes a body of training data D that consists of N input-output pairs (D = {(x (1) , y (1) ), (x (2) , y (2) ), . . . , (x (N ) , y (N ) )}).”
Weighted Constraints in Generative Linguistics (2009, background): “In the probabilistic model of grammar proposed by Johnson (2000, 2002), a candidate’s probability relative to the rest of the candidate set is proportional to the exponential of its harmony (often referred to as ‘‘Max-Ent-OT’’; see also Goldwater & Johnson, 2003; Jäger, 2007; Wilson, 2006).”
Gradual Learning and Convergence (2008, background): “…OT, other theories of variation in OT (e.g., Anttila 1997, Coetzee 2004, Jarosz 2006), and log-linear models of grammar that directly assign a probability distribution to the candidate set (Johnson 2002, Goldwater and Johnson 2003, Jäger and Rosenbach 2006, Wilson 2006, Jäger, to appear).”
Gradient Grammar: An Effect of Animacy on the Syntax of give in New Zealand and American English (2008, methodology): “…of probabilistic grammars to use and context is explained by statistical learning algorithms or by deriving their properties from models of language perception and production (Boersma and Hayes 2001, Boersma 2004, Ferreira 1996, Goldwater and Johnson 2003, Jäger in press, Chang et al. 2006).”
On the role of locality in learning stress patterns* (2009, background): “…1997, Boersma & Hayes 2001), minimum description length (Ellison 1991, Goldsmith & Riggle, ms), Bayes’ Law (Tenenbaum 1999, Goldwater 2006), maximum entropy (Goldwater & Johnson 2003, Hayes & Wilson 2008) and approaches inspired by Darwinian-like processes (Clark 1992, Yang 2000, Martin 2007).”
The winner takes it all — almost: cumulativity in grammatical variation (2006, result): “In the last part of the article, we compare the predictions of the two theories with respect to this empirical domain.”