Characterizing the Errors of Data-Driven Dependency Parsing Models

By Ryan T. McDonald, Joakim Nivre. Conference on Empirical Methods in Natural Language Processing, 2007

328 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/ef06ccbdab742b88f5eff8b46a61fa4cf7cfcbd8

How researchers see this paper

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

Citations in the corpus

The CoNLL 2007 Shared Task on Dependency Parsing (2007, methodology): “We then describe the two main paradigms for learning and inference, in this year’s shared task as well as in last year’s, which we call transition-based parsers (section 5.2) and graph-based parsers (section 5.3), adopting the terminology of McDonald and Nivre (2007).”
Transition-based Dependency Parsing with Rich Non-local Features (2011, result): “Compared to graph-based dependency parsing, it typically offers linear time complexity and the comparative freedom to deﬁne non-local features, as exempliﬁed by the comparison between MaltParser and MSTParser (Nivre et al., 2006b; Mc-Donald et al., 2005; McDonald and Nivre, 2007).”
Universal Dependencies v1: A Multilingual Treebank Collection (2016, methodology): “The Google universal tag set used in the morphological layer grew out of the cross-linguistic error analysis based on the CoNLL-X shared task data by McDonald and Nivre (2007).”
A Tale of Two Parsers: Investigating and Combining Graph-based and Transition-based Dependency Parsing (2008, methodology): “McDonald and Nivre (2007) showed that the MST-Parser and MaltParser produce different errors.”
From POS tagging to dependency parsing for biomedical event extraction (2018, background): “dencies are often modiers of nouns such as determiners or adjectives or pronouns modifying their direct neighbors, while longer dependencies typically represent modiers of the root or the main verb [43]. All parsers obtain higher scores for left dependencies than for right dependencies. This is not ”
Syntactic Processing Using the Generalized Perceptron and Beam Search (2011, background): “However, they make different types of errors, which can be seen as a reﬂection of their theoretical differences (McDonald and Nivre 2007).”
Training and Testing Low-degree Polynomial Data Mappings via Linear SVM (2010, background): “10 More information about dependency parsing can be found in, for example, McDonald and Nivre (2007). Dependency parsing appears in many online NLP applications.”
An Efficient Algorithm for Easy-First Non-Directional Dependency Parsing (2010, background): “This limited look-ahead window leads to error propagation and worse performance on root and long distant dependencies relative to graph-based parsers (McDonald and Nivre, 2007).”
Training Deterministic Parsers with Non-Deterministic Oracles (2013, methodology): “The error propagation problem for greedy transition-based parsing was diagnosed by McDonald and Nivre (2007) and has been tackled with a variety of techniques including parser stacking (Nivre and Mc-Donald, 2008; Martins et al., 2008) and beam search and structured prediction (Zhang and Clark,…”