Non-Deterministic Oracles for Unrestricted Non-Projective Transition-Based Dependency Parsing

Björkelund, Anders; Nivre, Joakim

doi:10.18653/v1/w15-2210

Cited by 15 publications

(12 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We apply an in-house transition-based beam search parser trained with the perceptron (Björkelund and Nivre, 2015), henceforth referred to as TP. 6 We have previously extended this parser to accommodate features from supertags (Faleńska et al, 2015).…”

Section: Transition-based Beam-perceptron Parsermentioning

confidence: 99%

IMS at the CoNLL 2017 UD Shared Task: CRFs and Perceptrons Meet Neural Networks

Björkelund

Faleńska

Xiang

et al. 2017

Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing From Raw Text to Universal Dependencies

Self Cite

View full text Add to dashboard Cite

This paper presents the IMS contribution to the CoNLL 2017 Shared Task. In the preprocessing step we employed a CRF POS/morphological tagger and a neural tagger predicting supertags. On some languages, we also applied word segmentation with the CRF tagger and sentence segmentation with a perceptron-based parser. For parsing we took an ensemble approach by blending multiple instances of three parsers with very different architectures. Our system achieved the third place overall and the second place for the surprise languages.

show abstract

Section: Transition-based Beam-perceptron Parsermentioning

confidence: 99%

IMS at the CoNLL 2017 UD Shared Task: CRFs and Perceptrons Meet Neural Networks

Björkelund

Faleńska

Xiang

et al. 2017

Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing From Raw Text to Universal Dependencies

Self Cite

View full text Add to dashboard Cite

show abstract

“…Dynamic oracles are at the heart of most state-ofthe-art parsers (Ballesteros et al, 2016;Coavoux and Crabbé, 2016;Cross and Huang, 2016;Kiperwasser and Goldberg, 2016). But, to the best of our knowledge, dynamic oracles have only been partially generalized to beam parsers: Björkelund and Nivre (2015)'s oracles address the second but not the first issue, while the dynamic oracle of the YaraParser (Rasooli and Tetreault, 2015) arbitrarily rules out some configurations that can generate the reference tree.…”

Section: Correction Of Training Biasesmentioning

confidence: 99%

Don't Stop Me Now! Using Global Dynamic Oracles to Correct Training Biases of Transition-Based Dependency Parsers

Aufrant¹,

Wisniewski²,

Yvon³

2017

Proceedings of the 15th Conference of the European Chapter of The Association for Computational Linguistics: Volume 2

View full text Add to dashboard Cite

This paper formalizes a sound extension of dynamic oracles to global training, in the frame of transition-based dependency parsers. By dispensing with the precomputation of references, this extension widens the training strategies that can be entertained for such parsers; we show this by revisiting two standard training procedures, early-update and max-violation, to correct some of their search space sampling biases. Experimentally, on the SPMRL treebanks, this improvement increases the similarity between the train and test distributions and yields performance improvements up to 0.7 UAS, without any computation overhead.

show abstract

“…arc-standard, arceager). Therefore, a large number of dynamic oracles have been developed in recent years (Goldberg and Nivre, 2012;Goldberg and Nivre, 2013;Goldberg et al, 2014;Gomez-Rodriguez et al, 2014;Björkelund and Nivre, 2015). In contrast, the reinforcement learning approach proposed in this paper is more general and can be applied to a variety of systems.…”

Section: Dependency Parsingmentioning

confidence: 99%

Tackling Error Propagation through Reinforcement Learning: A Case of Greedy Dependency Parsing

Fokkens

2017

Proceedings of the 15th Conference of the European Chapter of The Association for Computational Linguistics: Volume 1

View full text Add to dashboard Cite

Error propagation is a common problem in NLP. Reinforcement learning explores erroneous states during training and can therefore be more robust when mistakes are made early in a process. In this paper, we apply reinforcement learning to greedy dependency parsing which is known to suffer from error propagation. Reinforcement learning improves accuracy of both labeled and unlabeled dependencies of the Stanford Neural Dependency Parser, a high performance greedy parser, while maintaining its efficiency. We investigate the portion of errors which are the result of error propagation and confirm that reinforcement learning reduces the occurrence of error propagation.

show abstract

Non-Deterministic Oracles for Unrestricted Non-Projective Transition-Based Dependency Parsing

Cited by 15 publications

References 11 publications

IMS at the CoNLL 2017 UD Shared Task: CRFs and Perceptrons Meet Neural Networks

IMS at the CoNLL 2017 UD Shared Task: CRFs and Perceptrons Meet Neural Networks

Don't Stop Me Now! Using Global Dynamic Oracles to Correct Training Biases of Transition-Based Dependency Parsers

Tackling Error Propagation through Reinforcement Learning: A Case of Greedy Dependency Parsing

Contact Info

Product

Resources

About