Broad-Coverage Parsing with Neural Networks

Mayberry, Marshall R.; Miikkulainen, Risto

doi:10.1007/s11063-004-3423-4

Cited by 3 publications

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More recently, machine learning-based DP methods have been proposed for automatically classifying configurations into transition types for dependency relation extraction. Some of these efforts have focused on developing probabilistic models (e.g., Wang and Harper 2004;Collins 2003;Samuelsson 2000;Eisner 1996), while others have proposed discriminative approaches with support vector machines (e.g., Kudo and Matsumoto 2002;Yamada and Matsumoto 2003), beam search-based perceptron (e.g., Zhang and Nivre 2011; Zhang and Clark 2008), dynamic programming-based perceptron (e.g., Huang and Sagae 2010), or neural networks (e.g., Mayberry and Miikkulainen 2005;Henderson 2004). In recent years, there have been an increasing number of research efforts focusing on NN-based DP methods (e.g., Dozat and Manning 2018;Strubell and McCallum 2017;Nguyen et al 2017;Dozat and Manning 2017;Hashimoto et al 2017;Kuncoro et al 2017;Kiperwasser and Goldberg 2016;Cheng et al 2016;Yazdani and Henderson 2015;Alberti et al 2015;Weiss et al 2015;Dyer et al 2015;Chen and Manning 2014).…”

Section: Machine Learning-based Dependency Parsing Methodsmentioning

confidence: 99%

Semantic Neural Network Ensemble for Automated Dependency Relation Extraction from Bridge Inspection Reports

Liu

El-Gohary

2021

J. Comput. Civ. Eng.

View full text Add to dashboard Cite

Bridge inspection reports are important sources of technically detailed data/information about bridge conditions and maintenance history, yet remain untapped for bridge deterioration prediction. To capitalize on these reports for improved bridge deterioration prediction, there is a need for dependency parsing methods, in order to extract dependency relations from the reports for linking the isolated words into concepts and representing the semantically low concepts in a semantically rich structured way. To address this need, this paper proposes a novel semantic neural network ensemble (NNE)-based dependency parsing methodology. It uses a similarity-based method to sample similarly distributed configurations into the same clusters, a set of constituent neural network (NN) classifiers to learn from both the syntactic and semantic text features of the similarly distributed and therefore more easily separable configurations, and a combiner classifier to capture the classification patterns of the NN classifiers to make final predictions on the transition types. The proposed dependency parsing methodology was evaluated in extracting dependency relations from bridge inspection reports for representing information-about bridge conditions and maintenance actions-in a semantically rich structured way. It achieved a precision, recall, and F-1 measure of 96.6%, 90.4%, and 93.3% with a margin of error of 3.8%, 4.4%, and 3.8% at the semantic information element level, and 88.2%, 81.5%, and 84.7% with a margin of error of 5.4%, 5.8%, and 5.4% at the semantic information set level, respectively.

show abstract

Section: Machine Learning-based Dependency Parsing Methodsmentioning

confidence: 99%

Semantic Neural Network Ensemble for Automated Dependency Relation Extraction from Bridge Inspection Reports

Liu

El-Gohary

2021

J. Comput. Civ. Eng.

View full text Add to dashboard Cite

show abstract

A Fast and Accurate Dependency Parser using Neural Networks

Chen

Manning

2014

Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

1,414

1,291

View full text Add to dashboard Cite

Almost all current dependency parsers classify based on millions of sparse indicator features. Not only do these features generalize poorly, but the cost of feature computation restricts parsing speed significantly. In this work, we propose a novel way of learning a neural network classifier for use in a greedy, transition-based dependency parser. Because this classifier learns and uses just a small number of dense features, it can work very fast, while achieving an about 2% improvement in unlabeled and labeled attachment scores on both English and Chinese datasets. Concretely, our parser is able to parse more than 1000 sentences per second at 92.2% unlabeled attachment score on the English Penn Treebank.

show abstract

A Neural Probabilistic Structured-Prediction Model for Transition-Based Dependency Parsing

Zhou¹,

Zhang²,

Huang³

et al. 2015

Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Confere

View full text Add to dashboard Cite

Neural probabilistic parsers are attractive for their capability of automatic feature combination and small data sizes. A transition-based greedy neural parser has given better accuracies over its linear counterpart. We propose a neural probabilistic structured-prediction model for transition-based dependency parsing, which integrates search and learning. Beam search is used for decoding, and contrastive learning is performed for maximizing the sentence-level log-likelihood. In standard Penn Treebank experiments, the structured neural parser achieves a 1.8% accuracy improvement upon a competitive greedy neural parser baseline, giving performance comparable to the best linear parser.

show abstract

Broad-Coverage Parsing with Neural Networks

Cited by 3 publications

References 19 publications

Semantic Neural Network Ensemble for Automated Dependency Relation Extraction from Bridge Inspection Reports

Semantic Neural Network Ensemble for Automated Dependency Relation Extraction from Bridge Inspection Reports

A Fast and Accurate Dependency Parser using Neural Networks

A Neural Probabilistic Structured-Prediction Model for Transition-Based Dependency Parsing

Contact Info

Product

Resources

About