Improving dependency parsing with subtrees from auto-parsed data

Chen, Wenliang; Kazama, Jun'ichi; Uchimoto, Kiyotaka; Torisawa, Kentaro

doi:10.3115/1699571.1699587

Cited by 36 publications

(27 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…An advantage of the reranking framework used here is that it has no overlap with many of the semi-supervised parsing methods, such as word clustering [23] and subtree feature integration using auto-parsed data [24], [26], [29]. We are interested in studying the performance of our system when combined with these methods.…”

Section: Discussionmentioning

confidence: 99%

Dependency Parse Reranking with Rich Subtree Features

Shen

Kawahara

Kurohashi

2014

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

In pursuing machine understanding of human language, highly accurate syntactic analysis is a crucial step. In this work, we focus on dependency grammar, which models syntax by encoding transparent predicate-argument structures. Recent advances in dependency parsing have shown that employing higherorder subtree structures in graph-based parsers can substantially improve the parsing accuracy. However, the inefficiency of this approach increases with the order of the subtrees. This work explores a new reranking approach for dependency parsing that can utilize complex subtree representations by applying efficient subtree selection methods. We demonstrate the effectiveness of the approach in experiments conducted on the Penn Treebank and the Chinese Treebank. Our system achieves the best performance among known supervised systems evaluated on these datasets, improving the baseline accuracy from 91.88% to 93.42% for English, and from 87.39% to 89.25% for Chinese.

show abstract

Section: Discussionmentioning

confidence: 99%

Dependency Parse Reranking with Rich Subtree Features

Shen

Kawahara

Kurohashi

2014

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

show abstract

“…Learning more knowledge from large-scale corpus is a research trend [3], [9]. However a parser in general model has poor performance in special-case structure, no matter how huge the data is.…”

Section: Extracting and Learning Special-casesmentioning

confidence: 99%

Improving Chinese Parsing with Special-Case Probability Re-estimation

Hsieh

Lin

Chang

et al. 2013

2013 International Conference on Asian Language Processing

View full text Add to dashboard Cite

Syntactic patterns which are hard to be expressed by binary dependent relations need special treatments, since structure evaluations of such constructions are different from general parsing framework. Moreover, these different syntactic patterns (special cases) should be handled with distinct estimated model other than the general one. In this paper, we present a special-case probability re-estimation model (SCM), integrating the general model with an adoptable estimated model in special cases. The SCM model can estimate evaluation scores in specific syntactic constructions more accurately, and is able for adopting different features in different cases. Experiment results show that our proposed model has better performance than the state-of-the-art parser in Chinese.

show abstract

“…Dependency Parsing vVe use DuDuPlus2 as our dependency parser [6] and UAS3 to evaluate whether the coordinate word pairs can improve the performance on sentence which contains conjunction(s). The result on development set is shown in Table VI.…”

Section: A Datasetmentioning

confidence: 99%

Extracting coordinate word pairs for dependency parsing

Chen

2015

2015 International Conference on Asian Language Processing (IALP)

Self Cite

View full text Add to dashboard Cite

The subtask of identifying coordinate structures in Chinese dependency analysis is a chal lenging problem. The accuracy of coordinate word recognition remains below the average. To address this problem, we propose an automatic identification method based on large-scale unlabeled corpus. We then integrate a set of new features corresponding to the collected word pairs into the dependency parser. Specifically, our proposed method is based on the presence of easy-to-identify coordinate fragments. Our method can be divided into two steps. In the first step, we leverage two hand-crafted rules to extract highly accurate coordinate word pairs as seed words. The second step is to utilize seed words to extract coordinate structures in the corpus for further use of coordinate word pair extraction. Experimental results show that the extracted coordinate word pairs can sig nificantly improve the accuracy on coordinate structure dependency analysis. Index Terms-coordinate structure;dependency parsing;information extraction; 978-1-4673-95 96-0/15/$31.00 ©2015 IEEE 78

show abstract

Improving dependency parsing with subtrees from auto-parsed data

Cited by 36 publications

References 18 publications

Dependency Parse Reranking with Rich Subtree Features

Dependency Parse Reranking with Rich Subtree Features

Improving Chinese Parsing with Special-Case Probability Re-estimation

Extracting coordinate word pairs for dependency parsing

Contact Info

Product

Resources

About