Variational Bayesian Grammar Induction for Natural Language

By Kenichi Kurihara, Taisuke Sato. 2006

70 citations recorded by the source corpus.

How researchers see this paper

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

In Artificial Intelligence

Citations in the corpus

Variational Inference: A Review for Statisticians (2016, methodology): “…variational inference has been used for solving problems such as parsing (Liang et al. 2007; Liang, Jordan, and Klein 2009), grammar induction (Kurihara and Sato 2006; Naseem et al. 2010; Cohen and Smith 2010), models of streaming text (Yogatama et al. 2014), topic modeling (Blei, Ng, and…”
Covariance in Unsupervised Learning of Probabilistic Grammars (2010, methodology): “Variational approximations (Johnson, 2007; Kurihara and Sato, 2006) and randomized sampling approximations (Johnson et al., 2006; Goldwater, 2006) are typically app ied. Much of the Bayesian literature and its application to probabilistic grammars has f ocu ed on conjugate priorsin the form of Diric”
Compound Probabilistic Context-Free Grammars for Grammar Induction (2019, background): “In contrast to the usual Bayesian treatment of PCFGs which places priors on global rule probabilities (Kurihara and Sato, 2006; Johnson et al., 2007; Wang and Blunsom, 2013), the compound PCFG assumes a prior on local, sentence-level rule probabilities.”
Analyzing the Errors of Unsupervised Learning (2008, background): “Bayesian approaches can also improve performance (Goldwater and Grifﬁths, 2007; Johnson, 2007; Kurihara and Sato, 2006).”
The Infinite PCFG Using Hierarchical Dirichlet Processes (2007, background): “Kurihara and Sato (2004) and Kurihara and Sato (2006) applied variational inference to PCFGs.”
DreamCoder: bootstrapping inductive program synthesis with wake-sleep library learning (2021, background): “Other choices, such as Variational Bayes [26], may more closely approximate the marginal over θ , but are more complex and come at greater computational expense.”
Semantic Parsing with Bayesian Tree Transducers (2012, methodology): “Unfortunately, the introduction of a prior makes exact inference intractable, so we use an approximate method, variational Bayesian inference (Bishop, 2006), deriving an algorithm similar to that for PCFGs (Kurihara and Sato, 2006).”