A Classifier-Based Parser with Linear Run-Time Complexity
نویسندگان
چکیده
We present a classifier-based parser that produces constituent trees in linear time. The parser uses a basic bottom-up shiftreduce algorithm, but employs a classifier to determine parser actions instead of a grammar. This can be seen as an extension of the deterministic dependency parser of Nivre and Scholz (2004) to full constituent parsing. We show that, with an appropriate feature set used in classification, a very simple one-path greedy parser can perform at the same level of accuracy as more complex parsers. We evaluate our parser on section 23 of the WSJ section of the Penn Treebank, and obtain precision and recall of 87.54% and 87.61%, respectively.
منابع مشابه
A Fast, Accurate Deterministic Parser for Chinese
We present a novel classifier-based deterministic parser for Chinese constituency parsing. Our parser computes parse trees from bottom up in one pass, and uses classifiers to make shift-reduce decisions. Trained and evaluated on the standard training and test sets, our best model (using stacked classifiers) runs in linear time and has labeled precision and recall above 88% using gold-standard p...
متن کاملRecompiling a knowledge-based dependency parser into memory
Data-driven parsers tend to be trained on manually annotated treebanks. In this paper we describe two memory-based dependency parsers trained on treebanks that are automatically parsed by a knowledge-based parser for Dutch. When compared to training on a manual treebank of Dutch, the memory-based parsers exhibit virtually the same performance at the same amount of training material, and achieve...
متن کاملPolynomial Parsing of Contextual Grammars with Linear, Regular and Context–Free Selectors
In this paper, an intertwined two–level Earley–based parser is presented for some linguistically relevant classes of Contextual Grammars. The pure acceptor's space complexity is O(n 4) and its run time is O(n 6) according to the unrestricted recursion definition. With respect to maximal selectors, the space and time complexity runs up to O(n 6) and O(n 9), respectively. The same holds for the c...
متن کاملA Transition-Based Parser for 2-Planar Dependency Structures
Finding a class of structures that is rich enough for adequate linguistic representation yet restricted enough for efficient computational processing is an important problem for dependency parsing. In this paper, we present a transition system for 2-planar dependency trees – trees that can be decomposed into at most two planar graphs – and show that it can be used to implement a classifier-base...
متن کاملFace Detection with Support Vector Machines and a Very Large Set of Linear Features
This paper presents a fast and novel method to speed up training and evaluation of support vector machine (SVM) classifiers with a very large set of linear features. A pre-computation step and a redefinition of the kernel function handle linear feature evaluation implicitly and thus result in a run-time complexity as if no linear features were evaluated at all. We then train a classifier for fa...
متن کامل