It Depends: Dependency Parser Comparison Using A Web-based Evaluation Tool
نویسندگان
چکیده
The last few years have seen a surge in the number of accurate, fast, publicly available dependency parsers. At the same time, the use of dependency parsing in NLP applications has increased. It can be difficult for a non-expert to select a good “off-the-shelf” parser. We present a comparative analysis of ten leading statistical dependency parsers on a multi-genre corpus of English. For our analysis, we developed a new web-based tool that gives a convenient way of comparing dependency parser outputs. Our analysis will help practitioners choose a parser to optimize their desired speed/accuracy tradeoff, and our tool will help practitioners examine and compare parser output.
منابع مشابه
Feature Engineering in Persian Dependency Parser
Dependency parser is one of the most important fundamental tools in the natural language processing, which extracts structure of sentences and determines the relations between words based on the dependency grammar. The dependency parser is proper for free order languages, such as Persian. In this paper, data-driven dependency parser has been developed with the help of phrase-structure parser fo...
متن کاملIntrinsic versus Extrinsic Evaluations of Parsing Systems
A wide range of parser and/or grammar evaluation methods have been reported in the literature. However, in most cases these evaluations take the parsers independently (intrinsic evaluations), and only in a few cases has the effect of different parsers in real applications been measured (extrinsic evaluations). This paper compares two evaluations of the Link Grammar parser and the Conexor Functi...
متن کاملImproving cross-domain dependency parsing with dependency-derived clusters
This paper describes a semi-supervised approach to improving statistical dependency parsing using dependency-based word clusters. After applying a baseline parser to unlabeled text, clusters are induced using K-means with word features based on the dependency structures. The parser is then re-trained using information about the clusters, yielding improved parsing accuracy on a range of differen...
متن کاملParsPer: A Dependency Parser for Persian
We present a dependency parser for Persian, called ParsPer, developed using the graph-based parser in the Mate Tools. The parser is trained on the entire Uppsala Persian Dependency Treebank with a specific configuration that was selected by MaltParser as the best performing parsing representation. The treebank’s syntactic annotation scheme is based on Stanford Typed Dependencies with extensions...
متن کاملParser Evaluation and the BNC: Evaluating 4 constituency parsers with 3 metrics
We evaluate discriminative parse reranking and parser self-training on a new English test set using four versions of the Charniak parser and a variety of parser evaluation metrics. The new test set consists of 1,000 hand-corrected British National Corpus parse trees. We directly evaluate parser output using both the Parseval and the Leaf Ancestor metrics. We also convert the hand-corrected and ...
متن کامل