PanParser: a Modular Implementation for Efficient Transition-Based Dependency Parsing

Abstract We present PanParser, a Python framework dedicated to transition-based structured prediction, and notably suitable for dependency parsing. On top of providing an easy way to train state-of-the-art parsers, as empirically validated on UD 2.0, PanParser is especially useful for research purposes: its modular architecture enables to implement most state-of-the-art transition-based methods under the same unified framework (out of which several are already built-in), which facilitates fair benchmarking and allows for an exhaustive exploration of slight variants of those methods. PanParser additionally includes a number of fine-grained evaluation utilities, which have already been successfully leveraged in several past studies, to perform extensive error analysis of monolingual as well as cross-lingual parsing.

[1]  Slav Petrov,et al.  Globally Normalized Transition-Based Neural Networks , 2016, ACL.

[2]  Giorgio Satta,et al.  Dynamic Programming Algorithms for Transition-Based Dependency Parsers , 2011, ACL.

[3]  Danqi Chen,et al.  A Fast and Accurate Dependency Parser using Neural Networks , 2014, EMNLP.

[4]  Pontus Stenetorp,et al.  Transition-based Dependency Parsing Using Recursive Neural Networks , 2013 .

[5]  Slav Petrov,et al.  Structured Training for Neural Network Transition-Based Parsing , 2015, ACL.

[6]  Carlos Gómez-Rodríguez,et al.  An Efficient Dynamic Oracle for Unrestricted Non-Projective Parsing , 2015, ACL.

[7]  Joakim Nivre,et al.  Labeled Pseudo-Projective Dependency Parsing with Support Vector Machines , 2006, CoNLL.

[8]  François Yvon,et al.  Zero-resource Dependency Parsing: Boosting Delexicalized Cross-lingual Transfer with Linguistic Knowledge , 2016, COLING.

[9]  Joakim Nivre,et al.  Training Deterministic Parsers with Non-Deterministic Oracles , 2013, TACL.

[10]  Miguel Ballesteros,et al.  Automatic Feature Selection for Agenda-Based Dependency Parsing , 2014, COLING.

[11]  Jinho D. Choi,et al.  K -best, locally pruned, transition-based dependency parsing using robust risk minimization , 2009 .

[12]  Joakim Nivre,et al.  Non-Deterministic Oracles for Unrestricted Non-Projective Transition-Based Dependency Parsing , 2015, IWPT.

[13]  Yuji Matsumoto,et al.  Universal Dependencies 2.0 – CoNLL 2017 Shared Task Development and Test Data , 2017 .

[14]  Joakim Nivre,et al.  MaltOptimizer: An Optimization Tool for MaltParser , 2012, EACL.

[15]  François Yvon,et al.  Exploiting Dynamic Oracles to Train Projective Dependency Parsers on Non-Projective Trees , 2018, NAACL.

[16]  Joakim Nivre,et al.  Algorithms for Deterministic Incremental Dependency Parsing , 2008, CL.

[17]  Joakim Nivre,et al.  Joint Morphological and Syntactic Analysis for Richly Inflected Languages , 2013, TACL.

[18]  Xuanjing Huang,et al.  Transition-based Dependency Parsing Using Two Heterogeneous Gated Recursive Neural Networks , 2015, EMNLP.

[19]  Rudolf Rosa,et al.  KLcpos3 - a Language Similarity Measure for Delexicalized Parser Transfer , 2015, ACL.

[20]  Noah A. Smith,et al.  Training with Exploration Improves a Greedy Stack LSTM Parser , 2016, EMNLP.

[21]  Eneko Agirre,et al.  Improving Dependency Parsing with Semantic Classes , 2011, ACL.

[22]  Joakim Nivre,et al.  MaltParser: A Data-Driven Parser-Generator for Dependency Parsing , 2006, LREC.

[23]  Joakim Nivre,et al.  Squibs: Arc-Eager Parsing with the Tree Constraint , 2014, CL.

[24]  Joakim Nivre,et al.  A Transition-Based Parser for 2-Planar Dependency Structures , 2010, ACL.

[25]  Joakim Nivre,et al.  Non-Projective Dependency Parsing in Expected Linear Time , 2009, ACL.

[26]  Joakim Nivre,et al.  Squibs: Constrained Arc-Eager Dependency Parsing , 2014, CL.

[27]  Pierre Nugues,et al.  Automatic Discovery of Feature Sets for Dependency Parsing , 2010, COLING.

[28]  Carlos Gómez-Rodríguez,et al.  A Full Non-Monotonic Transition System for Unrestricted Non-Projective Parsing , 2017, ACL.

[29]  Stephen Clark,et al.  A Tale of Two Parsers: Investigating and Combining Graph-based and Transition-based Dependency Parsing , 2008, EMNLP.

[30]  Joakim Nivre,et al.  A Dynamic Oracle for Arc-Eager Dependency Parsing , 2012, COLING.

[31]  François Yvon,et al.  Frustratingly Easy Cross-Lingual Transfer for Transition-Based Dependency Parsing , 2016, NAACL.

[32]  Yoav Goldberg,et al.  An Efficient Algorithm for Easy-First Non-Directional Dependency Parsing , 2010, NAACL.

[33]  Joakim Nivre,et al.  Memory-Based Dependency Parsing , 2004, CoNLL.

[34]  Eliyahu Kiperwasser,et al.  Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations , 2016, TACL.

[35]  Emily Pitler,et al.  A Linear-Time Transition System for Crossing Interval Trees , 2015, NAACL.

[36]  Giorgio Satta,et al.  A Polynomial-Time Dynamic Oracle for Non-Projective Dependency Parsing , 2014, EMNLP.

[37]  Milan Straka,et al.  Tokenizing, POS Tagging, Lemmatizing and Parsing UD 2.0 with UDPipe , 2017, CoNLL.

[38]  Carlos Gómez-Rodríguez,et al.  A Dynamic Oracle for Linear-Time 2-Planar Dependency Parsing , 2018, NAACL.

[39]  François Yvon,et al.  LIMSI$@$CoNLL'17: UD Shared Task , 2017, CoNLL Shared Task.

[40]  Joakim Nivre,et al.  Incrementality in Deterministic Dependency Parsing , 2004 .

[41]  Yang Guo,et al.  Structured Perceptron with Inexact Search , 2012, NAACL.

[42]  Kai Zhao,et al.  Optimal Incremental Parsing via Best-First Dynamic Programming , 2013, EMNLP.

[43]  Joakim Nivre,et al.  Divisible Transition Systems and Multiplanar Dependency Parsing , 2013, CL.

[44]  Alon Lavie,et al.  Parser Combination by Reparsing , 2006, NAACL.

[45]  Joakim Nivre,et al.  Analyzing the Effect of Global Learning and Beam-Search on Transition-Based Dependency Parsing , 2012, COLING.

[46]  Philip Resnik,et al.  Cross-Language Parser Adaptation between Related Languages , 2008, IJCNLP.

[47]  Mark Johnson,et al.  An Improved Non-monotonic Transition System for Dependency Parsing , 2015, EMNLP.

[48]  Martin Haulrich.  Transition-Based Parsing with Confidence-Weighted Classification , 2010, ACL.

[49]  Joakim Nivre,et al.  Squibs: Going to the Roots of Dependency Parsing , 2013, CL.

[50]  Noah A. Smith,et al.  Greedy, Joint Syntactic-Semantic Parsing with Stack LSTMs , 2016, CoNLL.

[51]  Giorgio Satta,et al.  A Tabular Method for Dynamic Oracles in Transition-Based Parsing , 2014, TACL.

[52]  Carlos Gómez-Rodríguez,et al.  Improving Transition-Based Dependency Parsing with Buffer Transitions , 2012, EMNLP.

[53]  Michael A. Covington,et al.  A Fundamental Algorithm for Dependency Parsing , 2004 .

[54]  Christopher D. Manning,et al.  Arc-swift: A Novel Transition System for Dependency Parsing , 2017, ACL.

[55]  Mark Johnson,et al.  A Non-Monotonic Arc-Eager Transition System for Dependency Parsing , 2013, CoNLL.

[56]  Kenji Sagae,et al.  Dynamic Programming for Linear-Time Incremental Parsing , 2010, ACL.

[57]  François Yvon,et al.  Don't Stop Me Now! Using Global Dynamic Oracles to Correct Training Biases of Transition-Based Dependency Parsers , 2017, EACL.

[58]  Brian Roark,et al.  Incremental Parsing with the Perceptron Algorithm , 2004, ACL.

[59]  Carlos Gómez-Rodríguez,et al.  Non-Projective Dependency Parsing with Non-Local Transitions , 2017, NAACL.

[60]  François Yvon,et al.  Ne nous arrêtons pas en si bon chemin : améliorations de l'apprentissage global d'analyseurs en dépendances par transition (Don't Stop Me Now ! Improved Update Strategies for Global Training of Transition-Based) , 2016, JEP-TALN-RECITAL.

[61]  Timothy Dozat,et al.  Deep Biaffine Attention for Neural Dependency Parsing , 2016, ICLR.

[62]  Joakim Nivre,et al.  Transition-based Dependency Parsing with Rich Non-local Features , 2011, ACL.

[63]  Joakim Nivre,et al.  Arc-Hybrid Non-Projective Dependency Parsing with a Static-Dynamic Oracle , 2017, IWPT.

[64]  Joakim Nivre,et al.  An Efficient Algorithm for Projective Dependency Parsing , 2003, IWPT.

[65]  Fernando Pereira,et al.  Non-Projective Dependency Parsing using Spanning Tree Algorithms , 2005, HLT.

[66]  Slav Petrov,et al.  Improved Transition-Based Parsing and Tagging with Neural Networks , 2015, EMNLP.

[67]  Yoav Goldberg,et al.  Efficient Implementation of Beam-Search Incremental Parsers , 2013, ACL.