Max-Margin Tensor Neural Network for Chinese Word Segmentation

Pei, Wenzhe; Ge, Tao; Chang, Baobao

doi:10.3115/v1/p14-1028

Cited by 149 publications

(170 citation statements)

References 13 publications

Supporting

Mentioning

164

Contrasting

Order By: Relevance

“…Pretraining further improves the performance of all three models, which is consistent with the conclusion of previous work (Pei et al, 2014;Chen and Manning, 2014). Moreover, 1-order-phrase performs better than 1-order-atomic, which shows that phrase embeddings do improve the model.…”

Section: Experiments Resultssupporting

confidence: 79%

“…It is shown that similar features will have similar embeddings which capture the syntactic and semantic information behind features (Bengio et al, 2003; Collobert et al, 2011;Schwenk et al, 2012;Mikolov et al, 2013;Socher et al, 2013;Pei et al, 2014).…”

Section: Feature Embeddingsmentioning

confidence: 99%

“…Socher et.al (2013) and Pei et.al (2014) used a tensor-based activation function to learn feature combinations. However, tensor-based transformation is quite slow even with tensor factorization (Pei et al, 2014). Chen and Manning (2014) proposed to use cube function g(l) = l 3 which inspires our tanh-cube function.…”

Section: Learning Feature Combinationmentioning

confidence: 99%

See 2 more Smart Citations

An Effective Neural Network Model for Graph-based Dependency Parsing

Pei

Chang

2015

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

Self Cite

View full text Add to dashboard Cite

Most existing graph-based parsing models rely on millions of hand-crafted features, which limits their generalization ability and slows down the parsing speed. In this paper, we propose a general and effective Neural Network model for graph-based dependency parsing. Our model can automatically learn high-order feature combinations using only atomic features by exploiting a novel activation function tanhcube. Moreover, we propose a simple yet effective way to utilize phrase-level information that is expensive to use in conventional graph-based parsers. Experiments on the English Penn Treebank show that parsers based on our model perform better than conventional graph-based parsers.

show abstract

Section: Experiments Resultssupporting

confidence: 79%

Section: Feature Embeddingsmentioning

confidence: 99%

See 1 more Smart Citation

An Effective Neural Network Model for Graph-based Dependency Parsing

Pei

Chang

2015

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

Self Cite

View full text Add to dashboard Cite

show abstract

“…A comprehensive survey is out of the scope of this paper, but interested readers can refer to Pei et al (Pei et al, 2014) for a recent literature review of the fields.…”

Section: Related Workmentioning

confidence: 99%

A Transition-based Model for Joint Segmentation, POS-tagging and Normalization

Qian

Zhang

et al. 2015

Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

We propose a transition-based model for joint word segmentation, POS tagging and text normalization. Different from previous methods, the model can be trained on standard text corpora, overcoming the lack of annotated microblog corpora. To evaluate our model, we develop an annotated corpus based on microblogs. Experimental results show that our joint model can help improve the performance of word segmentation on microblogs, giving an error reduction in segmentation accuracy of 12.02%, compared to the traditional approach.

show abstract

“…Recently, neural network has gained increasing research attention, with highly competitive results being reported for numerous NLP tasks, including word segmentation (Zheng et al, 2013;Pei et al, 2014;, POS-tagging (Ma et al, 2014;Plank et al, 2016), and parsing (Chen and Manning, 2014; Dyer et al, 2015;Weiss et al, 2015;. On the other hand, the aforementioned methods on heterogeneous annotations are investigated mainly for discrete models.…”

Section: Introductionmentioning

confidence: 99%

Neural Network for Heterogeneous Annotations

Chen¹,

Zhang²,

Li³

2016

Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Multiple treebanks annotated under heterogeneous standards give rise to the research question of best utilizing multiple resources for improving statistical models. Prior research has focused on discrete models, leveraging stacking and multi-view learning to address the problem. In this paper, we empirically investigate heterogeneous annotations using neural network models, building a neural network counterpart to discrete stacking and multiview learning, respectively, finding that neural models have their unique advantages thanks to the freedom from manual feature engineering. Neural model achieves not only better accuracy improvements, but also an order of magnitude faster speed compared to its discrete baseline, adding little time cost compared to a neural model trained on a single treebank.

show abstract

Max-Margin Tensor Neural Network for Chinese Word Segmentation

Cited by 149 publications

References 13 publications

An Effective Neural Network Model for Graph-based Dependency Parsing

An Effective Neural Network Model for Graph-based Dependency Parsing

A Transition-based Model for Joint Segmentation, POS-tagging and Normalization

Neural Network for Heterogeneous Annotations

Contact Info

Product

Resources

About