An Efficient Algorithm for Easy-First Non-Directional Dependency Parsing

By Yoav Goldberg, Michael Elhadad. 2010

219 citations recorded by the source corpus.

Subfields: Natural Language Processing, Information Extraction

How researchers see this paper

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

In Natural Language Processing

In Information Extraction

Citations in the corpus

Solving Hard Coreference Problems (2019, methodology): “The extraction of triples is done by utilizing the dependency parse tree from the Easy-ﬁrst dependency parser (Goldberg and Elhadad, 2010).”
A Primer on Neural Network Models for Natural Language Processing (2015, background): “…(Socher, Manning, & Ng, 2010; Socher, Lin, Ng, & Manning, 2011; Socher et al., 2013; Socher, 2014) is a generalization of the RNN from sequences to (binary) trees.37 Much like the RNN encodes each sentence prefix as a state vector, the RecNN encodes each tree-node as a state vector in Rd.”
Easy-First Dependency Parsing with Hierarchical Tree LSTMs (2016, methodology): “This window approach is also used in the Easy-First parser of Goldberg and Elhadad (Goldberg and Elhadad, 2010) and works that extend it (Tratz and Hovy, 2011; Ma et al., 2012; Ma et al., 2013).”
Identifying Broken Plurals, Irregular Gender, and Rationality in Arabic Text (2012, methodology): “The parser we use is the Easy-First Parser (Goldberg and Elhadad, 2010).”
Visually Grounded Neural Syntax Acquisition (2019, unknown): “VG-NSL starts by composing a binary constituency structure of text, using an easy-first bottom-up parser (Goldberg and Elhadad, 2010).”
Learning What’s Easy: Fully Differentiable Neural Easy-First Taggers (2017, methodology): “Easy-ﬁrst decoders (Tsuruoka and Tsujii, 2005; Goldberg and Elhadad, 2010, § 2) are an interesting alternative: instead of a ﬁxed decoding order, these methods schedule their own actions by prefering “easier” decisions over more difﬁ-cult ones.”
Visually Grounded Compound PCFGs (2020, methodology): “The parsing model is an easy-ﬁrst parser (Goldberg and Elhadad, 2010).”
Discriminative Syntax-Based Word Ordering for Text Generation (2015, methodology): “Following Wan et al. (2009), we use the BLEU metric (Papineni et al. 2002) for string comparison.”
Learning to Compose Task-Specific Tree Structures (2017, background): “It is notable that the property of selecting the best node pair at each stage resembles that of easy-first parsing (Goldberg and Elhadad 2010).”
Training Deterministic Parsers with Non-Deterministic Oracles (2013, methodology): “Using this framework, we derive novel dynamic oracles for the hybrid (Kuhlmann et al., 2011) and easy-ﬁrst (Goldberg and Elhadad, 2010) transition systems, which are arc-decomposable (as is the arc-eager system).”
Non-Monotonic Sequential Text Generation (2019, background): “…orders are worth considering (Ford et al., 2018), especially given the success of “easy ﬁrst” techniques in natural language tagging (Tsuruoka & Tsujii, 2005), parsing (Goldberg & Elhadad, 2010), and coreference (Stoyanov & Eisner, 2012), which allow a model to effectively learn their own ordering.”
Chained Predictions Using Convolutional Neural Networks (2016, background): “Prior work in sequential modelling has explored the idea of choosing the best ordering for a task [10,11,12].”
Transition-based Dependency Parsing with Rich Non-local Features (2011, methodology): “2 Following Huang and Sagae (2010), we assign POS-tags to the training data using ten-way jackknifing.”
Modeling Joint Entity and Relation Extraction with Table Representation (2014, methodology): “Easy-first policy was firstly introduced by Goldberg and Elhadad (2010) for dependency parsing, and it was successfully employed in several tasks, such as joint POS tagging and dependency parsing (Ma et al.”