Computation of the Probability of Initial Substring Generation by Stochastic Context-Free Grammars

By Frederick Jelinek, John D. Lafferty. 1991

Subfields: Computational Linguistics & Semantics

How researchers see this paper

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

In Computational Linguistics & Semantics

Citations in the corpus

Recurrent Neural Network Grammars (2016, background): “Syntactic language models jointly generate a syntactic structure and a sequence of words (Baker, 1979; Jelinek and Lafferty, 1991).”
Recognition of Visual Activities and Interactions by Stochastic Parsing (2000, methodology): “In order to demonstrate the solution, we first need to introduce the concept of Left Corner Relation [ 20 ].”
A Probabilistic Earley Parser as a Psycholinguistic Model (2001, background): “3), many speech researchers (Jelinek and Lafferty, 1991) sought to incorporate hierarchical phrase structure into language modeling (see (Stolcke, 1997)) although it was not until the late 1990s that such models were able to significantly improve on 3-grams (Chelba and Jelinek, 1998).”
Expectation-based syntactic comprehension. (2008, methodology): “String prefix probabilities can be calculated efficiently as a byproduct of bottom-up or left-to-right parsing algorithms, as specified by Jelinek and Lafferty (1991) or Stolcke (1995). PCFG estimation is the process of selecting a set of rules and associated probabilities.”
Discoverer: Automatic Protocol Reverse Engineering from Network Traces (2007, methodology): “Techniques used in the speech recognition community, such as, probabilistic Markov chain analysis [8], were not applied in our work, since the correlation between protocol fields makes it difficult for the byte sequence in a message to be modeled as independent samples from a Markov process.”
Representing word meaning and order information in a composite holographic lexicon. (2007, background): “…refers specifically to sequence chunks of n words encountered during learning (the term is also often used to refer to sequences of letters within a word). chastic context-free grammars (Booth, 1969) learn probabilities for production rules from training data (e.g., Jelinek & Lafferty, 1991).”