Syntactic Processing

By M. Kay. 1979

In computational linguistics, which began in the 1950's with machine translation, systems that are based mainly on the lexicon have a longer t r a d i t i o n than anything e l se f o r these purposes, twenty f i ve years must be allowed to count as a tradition. The bulk of many of the early translation systems was made up by a d ic t ionary whose ent r ies consisted of a rb i t ra ry ins t ruc t ions In machine language. In the early 60's, computational llnsulsts---at least those with theoretical pretentlons---abandoned this way of doing business for at least three related reasons:

Subfields: Natural Language Processing

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

Grammar-Based Grounded Lexicon Learning (2022, background): “The lexicalist theories of syntax [30, 37, 9] propose that 1) the key syntactic principles by which words and phrases combine are extremely simple and general, and 2) nearly all of the complexity in syntax can be attributed to rich and detailed lexical entries for the words in the language.”
Language Modeling with Gated Convolutional Networks (2016, background): “Analyzing the input hierarchically bears resemblance to classical grammar formalisms which build syntactic tree structures of increasing granuality, e.g., sentences consist of noun phrases and verb phrases each comprising further internal structure (Manning & Sch ¨ utze, 1999; Steedman, 2002).”
Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars (2005, methodology): “The grammar formalism we use is combinatory categorial grammar (CCG) (Steedman, 1996, 2000).”
The Web as a Knowledge-Base for Answering Complex Questions (2018, methodology): “This is similar to function composition in CCG (Steedman, 2000), or a join operation in λ-DCS (Liang, 2013), where the string is a function applied to previously-computed values.”
Learning Dependency-Based Compositional Semantics (2011, neutral): “CCG (Steedman 2000) is quite popular in computational linguistics (for example, see Bos et al.”
Weakly Supervised Learning of Semantic Parsers for Mapping Instructions to Actions (2013, background): “Starting from lexical entries, each intermediate parse node, including syntax and semantics, is constructed with one of a small set of CCG combinators (Steedman, 1996, 2000).”
Scaling Semantic Parsers with On-the-Fly Ontology Matching (2013, methodology): “Combinatory Categorial Grammars (CCG) CCGs are a linguistically-motivated formalism for modeling a wide range of language phenomena (Steedman, 1996, 2000).”
Learning Context-Dependent Mappings from Sentences to Logical Form (2009, methodology): “Finally, the CCG (Steedman, 1996; Steedman, 2000) parsing setup is closely related to previous CCG research, including work on learning parsing models (Clark and Curran, 2003), wide-coverage semantic parsing (Bos et al., 2004) and grammar induction (Watkinson and Manandhar, 1999).”
Automatically Solving Number Word Problems by Semantic Parsing and Reasoning (2015, background): “Abstract Meaning Representation (AMR) (Banarescu et al., 2013) keeps richer semantic information than CCG and logical forms.”
Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation (2017, methodology): “It is common for contemporary planningbased approaches to nlg to be couched in the formalism of Lexicalised Tree Adjoining Grammar (ltag; Joshi & Schabes, 1997), though other formalisms, such as Combinatory Categorial Grammar (Steedman, 2000) have also been shown to be adequate to the task (see espe”
Experimental Support for a Categorical Compositional Distributional Model of Meaning (2011, methodology): “via cosine measure or k-means clustering), as discussed in Widdows (2005). The principal drawback of such models is their non-compositional nature: they ignore grammatical structure and logical words, and hence cannot compute the meanings of phrases and sentences in the same efficient way that they ”
Learning executable semantic parsers for natural language understanding (2016, background): “One common approach to the grammar in semantic parsing is combinatory categorial grammar (CCG) [28], which had been developed extensively in linguistics before it was ﬁrst used for semantic parsing [37].”
Contrasting intrusion profiles for agreement and anaphora: Experimental and modeling evidence (2013, background): “…of the syntactic retrieval process observed for reflexives is linked to the argument structure of the verb, which some theoretical accounts of binding relationships hold to be of central importance in describing the distribution of reflexive anaphors (e.g., Pollard & Sag, 1992; Steedman, 2000).”
Programming With Unrestricted Natural Language (2005, background): “Combinatory Categorial Grammar (CCG) is a typedriven, lexicalised theory of grammar (Steedman, 2000).”
Multimodal child-robot interaction: building social bonds (2013, methodology): “Alternatively, the output could be a logical form that would serve as input into a grammar-based lexical realization component using OpenCCG.”
The time-course of prediction in incremental sentence processing: Evidence from anticipatory eye-movements (2003, background): “In some grammatical theories such a component is made quite explicit (cf. Combinatory Categorical Grammar; e.g., Steedman, 2000).”
Wide-Coverage Efficient Statistical Parsing with CCG and Log-Linear Models (2007, methodology): “The algorithm used to build the packed charts is the CKY chart parsing algorithm (Kasami 1965; Younger 1967) described in Steedman (2000).”