Using Prior Knowledge in a {NNPDA} to Learn Context-Free Languages

By Sreerupa Das, C. Lee Giles, Guo-Zheng Sun. 1992

How researchers see this paper

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

In Natural Language Processing

Citations in the corpus

Inferring Algorithmic Patterns with Stack-Augmented Recurrent Nets (2015, methodology): “This type of model has been widely used in the early nineties with some encouraging success (Das et al., 1992; 1993; Zeng et al., 1994; Holldobler et al., 1997; Mozer & Das, 1993).”
Neural Programmer: Inducing Latent Programs with Gradient Descent (2015, background): “While there has been lot of work in augmenting neural networks with additional memory (Das et al., 1992a; Schmidhu-ber, 1993; Hochreiter & Schmidhuber, 1997; Graves et al., 2014; Weston et al., 2015; Kumar et al., 2015; Joulin & Mikolov, 2015), we are not aware of any other work that augments a…”
Learning to Transduce with Unbounded Memory (2015, background): “Previous work has touched on the topic of rendering discrete data structures such as stacks continuous, especially within the context of modelling pushdown automata with neural networks [10, 11, 3, 12].”
TerpreT: A Probabilistic Programming Language for Program Induction (2016, background): “The hypothesis space of possible programs is typically defined using a domain-specific language, which is designed to be expressive enough to encode majority of desired tasks but at the same time concise enough for efficient 3Interestingly enough, extracting an interpretable deterministic pushdown a”
Context-free and context-sensitive dynamics in recurrent neural networks (2000, methodology): “RNNs have been handcrafted, sometimes using external stacks, to handle context-free (Das et al., 1993; Zeng et al., 1994; H olldobler et al., 1997; Tabor, 2000) and context-sensitive languages (Steijvers and Gr unwald, 1996).”
Connectionist Theory Refinement: Genetically Searching the Space of Network Topologies (1997, unknown): “…1989; Lacher et al., 1992; Mahoney & Mooney, 1993), (cid:12)nite-state automata (Maclin & Shavlik, 1993; Omlin & Giles, 1992), push-down automata (Das, Giles, & Sun, 1992), fuzzy-logic rules (Berenji, 1991; Masuoka, Watanabe, Kawamura, Owada, & Asakawa, 1990), and mathematical equations…”
Rule Extraction from Recurrent Neural Networks: ATaxonomy and Review (2005, methodology): “…machines into RNNs (rule insertion) and/or for transforming RNNs into state machines (rule extraction) (e.g. Omlin & Giles 1992, Giles & Omlin 1993, Das, Giles & Sun 1993, Alqu´ezar & Sanfeliu 1994 a , Omlin & Giles 1996 a , Omlin & Giles 1996 c , Omlin, Thornber & Giles 1998, Omlin & Giles 2000,…”
Incremental training of first order recurrent neural networks to predict a context-sensitive language (2003, background): “string length) either helped to improve learning (Das et al., 1993; Elman, 1993) or appeared to impose some restrictions on the way networks developed during the learning process which finally inhibited successful learning (Rohde & Plaut, 1997, 1999, 2003; Zeng et al.”
Discrete recurrent neural networks for grammatical inference (1994, methodology): “Das er al. have suggested in [ 3 ] that by providing the network with a “teacher” or an “oracle” to give hints, the leaming can be sped up significantly.”
Fractal encoding of context‐free grammars in connectionist networks (2000, methodology): “Many have used an external stack (Giles et al ., 1990; Sun et al ., 1990; Das et al ., 1993; Mozer & Das, 1993; Zheng et al ., 1994).”