ML-Tuned Constraint Grammars
نویسنده
چکیده
In this paper we present a new method for machine learning-based optimization of linguist-written Constraint Grammars. The effect of rule ordering/sorting, grammarsectioning and systematic rule changes is discussed and quantitatively evaluated. The F-score improvement was 0.41 percentage points for a mature (Danish) tagging grammar, and 1.36 percentage points for a half-size grammar, translating into a 7-15% error reduction relative to the performance of the untuned grammars.
منابع مشابه
Flexible Corpus Annotation with Property Grammars
We present in this paper a syntactic annotation project relying on a linguistic formalism called Property Grammars. This constraint-based formalism allows to encode different levels of syntactic information (the granularity description can be tuned according to the set of constraints to be verified). Moreover, this approach allows to propose a description whatever the form of the input (being i...
متن کاملA parameter-tuned genetic algorithm for vendor managed inventory model for a case single-vendor single-retailer with multi-product and multi-constraint
This paper develops a single-vendor single-retailer supply chain for multi-product. The proposed model is based on Vendor Managed Inventory (VMI) approach and vendor uses the retailer's data for better decision making. Number of orders and available capital are the constraints of the model. In this system, shortages are backordered; therefore, the vendor’s warehouse capacity is another limitati...
متن کاملCorpus-based Learning of Ot Constraint Rankings for Large-scale Lfg Grammars
We discuss a two-stage disambiguation technique for linguistically precise broad-coverage grammars: the pre-filter of the first stage is triggered by linguistic configurations (“optimality marks”) specified by the grammar writer; the second stage is a log-linear probability model trained on corpus data. This set-up is used in the Parallel Grammar (ParGram) project, developing Lexical Functional...
متن کاملRestricted Global Grammar Constraints
We investigate the global GRAMMAR constraint over restricted classes of context free grammars like deterministic and unambiguous context-free grammars. We show that detecting disentailment for the GRAMMAR constraint in these cases is as hard as parsing an unrestricted context free grammar. We also consider the class of linear grammars and give a propagator that runs in quadratic time. Finally, ...
متن کاملConstraint Relation Multiset Grammars for Visual Languages
This paper proposes grammars for visual languages. The proposed grammars introduce relations into the constraint multiset grammars[4J. Relations are the constraints on the relationships among symbols in visual languages. The proposed grammars. which are called constraint relation multiset grammars. have the relations as the first class citizens of the grammars because the relationships among sy...
متن کامل