Transition-based Dependency Parsing with Rich Non-local Features

By Yue Zhang, Joakim Nivre. 2011

372 citations recorded by the source corpus.

Subfields: Information Extraction, Computational Linguistics & Semantics

How researchers see this paper

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

In Information Extraction

In Computational Linguistics & Semantics

Citations in the corpus

Parallel Data, Tools and Interfaces in OPUS (2012, background): “1 models, “zpar” refers to a statistical parser with language-specific features for Chinese and English (Zhang and Nivre, 2011), SVMTool (Giménez and Màrquez, 2004) and MElt (Denis and Sagot, 2009) are statistical taggers with language-specific models required for the respective dependency parser mo”
A Fast and Accurate Dependency Parser using Neural Networks (2014, methodology): “And following (Zhang and Clark, 2008; Zhang and Nivre, 2011), we use gold segmentation and POS tags for the input.”
Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations (2016, methodology): “Examples of good feature functions are the feature-set proposed by Zhang and Nivre (2011) for transition-based parsing (including roughly 20 core components and 72 feature templates), and the feature-set proposed by McDonald et al (2005) for graph-based parsing, with the paper listing 18 templates…”
Easy-First Dependency Parsing with Hierarchical Tree LSTMs (2016, background): “ those of the base parsers they use. O(n)+ indicates a linear-time system with a large multiplicative constant. The different systems and the numbers reported from them are taken from: ZhangNivre11: (Zhang and Nivre, 2011); Martins13: (Martins et al., 2013); Weiss15 (Weiss et al., 2015); Pei15: (Pei”
Vine Pruning for Efficient Multi-Pass Dependency Parsing (2012, neutral): “Our pruned third-order model is faster than an unpruned ﬁrst-order model, and compares favorably in speed to the state-of-the-art transition-based parser of Zhang and Nivre (2011).”
Parsing as Pretraining (2020, background): “For instance, in transition-based dependency parsers it was common to refer to daughter or grand-daughter features of a given term in the stack or the buffer, in order to provide these models with more contextual information (Zhang and Nivre 2011).”
Turning on the Turbo: Fast Third-Order Non-Projective Turbo Parsers (2013, methodology): “Third-order features have also been included in transition systems (Zhang and Nivre, 2011) and graph-based parsers with cube-pruning (Zhang and McDonald, 2012).”
A Bayesian Model for Generative Transition-based Dependency Parsing (2015, methodology): “Despite these promising results, our model’s performance still lags behind recent discriminative parsers (Zhang and Nivre, 2011; Choi and McCallum, 2013) with beam-search and richer feature sets than can be incorporated in our model.”
Stack-Pointer Networks for Dependency Parsing (2018, methodology): “, 2007): local and greedy transitionbased algorithms (Yamada and Matsumoto, 2003; Nivre and Scholz, 2004; Zhang and Nivre, 2011; Chen and Manning, 2014), and the globally optimized graph-based algorithms (Eisner, 1996; McDonald et al.”
Structured Training for Neural Network Transition-Based Parsing (2015, background): “We use same setup as Li et al. (2014), intersecting the output of the BerkeleyParser (Petrov et al., 2006), and a reimplementation of ZPar (Zhang and Nivre, 2011) as our baseline parsers.”
A Review on Language Models as Knowledge Bases (2022, neutral): “(Och et al., 2004; Zhang and Nivre, 2011) and architecture engineering (Chung et al.”
YSDA Participation in the WMT’16 Quality Estimation Shared Task (2016, methodology): “To collect this information we used an implementation of dependency parser described in (Zhang and Nivre, 2011), trained for English and German.”
Discriminative Syntax-Based Word Ordering for Text Generation (2015, positive): “Table 2 shows the feature templates we use, which are inspired by the rich feature templates used for dependency parsing (Koo and Collins 2010; Zhang and Nivre 2011).”
Ambiguity-aware Ensemble Training for Semi-supervised Dependency Parsing (2014, methodology): “…directed graph (McDonald et al., 2005; McDonald and Pereira, 2006; Carreras, 2007; Koo and Collins, 2010), while the transition-based method tries to ﬁnd a highest-scoring transition sequence that leads to a legal dependency tree (Yamada and Matsumoto, 2003; Nivre, 2003; Zhang and Nivre, 2011).”
Semantic Frame Identification with Distributed Word Representations (2014, methodology): “…our PropBank and FrameNet training, development and test corpora with a shift-reduce dependency parser that uses the Stanford conventions (de Marneffe and Manning, 2013) and uses an arc-eager transition system with beam size of 8; the parser and its features are described by Zhang and Nivre (2011).”
Fast and Accurate Shift-Reduce Constituent Parsing (2013, background): “In addition, processing tens of sentences per second (Zhang and Nivre, 2011), these transition-based parsers can be a favorable choice for dependency parsing.”
Universal Dependency Annotation for Multilingual Parsing (2013, methodology): “We use the features of Zhang and Nivre (2011), except that all lexical identities are dropped from the templates during training and testing, hence inducing a ‘delexical-ized’ model that employs only ‘universal’ properties from source-side treebanks, such as part-of-speech tags, labels,…”