Dependency grammar induction via bitext projection constraints

Ganchev, Kuzman; Gillenwater, Jennifer; Taskar, Ben

doi:10.3115/1687878.1687931

Cited by 68 publications

(76 citation statements)

References 23 publications

(29 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ganchev et al (2009) presented a parser projection approach via parallel text using the posterior regularization framework (Graca et al, 2007). proposed two parser transfer approaches between two different languages -one is directly transferred parser from delexicalized parsers, and the other parser is transferred using constraint driven learning algorithm where constraints are drawn from parallel corpora.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Dependency Parsing with Transferring Distribution via Parallel Guidance and Entropy Regularization

Xia

2014

Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

We present a novel approach for inducing unsupervised dependency parsers for languages that have no labeled training data, but have translated text in a resourcerich language. We train probabilistic parsing models for resource-poor languages by transferring cross-lingual knowledge from resource-rich language with entropy regularization. Our method can be used as a purely monolingual dependency parser, requiring no human translations for the test data, thus making it applicable to a wide range of resource-poor languages. We perform experiments on three Data sets -Version 1.0 and version 2.0 of Google Universal Dependency Treebanks and Treebanks from CoNLL shared-tasks, across ten languages. We obtain stateof-the art performance of all the three data sets when compared with previously studied unsupervised and projected parsing systems.

show abstract

Section: Introductionmentioning

confidence: 99%

Unsupervised Dependency Parsing with Transferring Distribution via Parallel Guidance and Entropy Regularization

Xia

2014

Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

show abstract

“…Besides, " " is mostly used in old Japanese society or to indicate old male characters, while " " is frequently used by young girls. syntax projection across languages (Yarowsky and Ngai 2001;Hwa et al 2005;Kuzman Ganchev and Taskar 2009) and unsupervised syntax induction in multiple languages (Snyder et al 2009), as well as other tasks, such as cross-lingual named entity recognition (Huang and Vogel 2002;Moore 2003;Wang and Manning 2014) and information retrieval (Si and Callan 2005). In all of these cases, multilingual models yield increased accuracy because different languages present different ambiguities and therefore offer complementary constraints on the shared underlying labels.…”

Section: Pronouns In English Chinese and Japanesementioning

confidence: 99%

A novel and robust approach for pro-drop language translation

Wang

Zhang

et al. 2017

Machine Translation

View full text Add to dashboard Cite

A significant challenge for machine translation (MT) is the phenomena of dropped pronouns (DPs), where certain classes of pronouns are frequently dropped in the source language but should be retained in the target language. In response to this common problem, we propose a semi-supervised approach with a universal framework to recall missing pronouns in translation. Firstly, we build training data for DP generation in which the DPs are automatically labelled according to the alignment information from a parallel corpus. Secondly, we build a deep learning-based DP generator for input sentences in decoding when no corresponding references exist. More specifically, the generation has two phases: (1) DP position detection, which is modeled as a sequential labelling task with recurrent neural networks; and (2) DP prediction, which employs a multilayer perceptron with rich features. Finally, we integrate the above outputs into our statistical MT (SMT) system to recall missing pronouns by both extracting rules from the DP-labelled training data and translating the DPgenerated input sentences. To validate the robustness of our approach, we investigate our approach on both Chinese-English and Japanese-English corpora extracted from movie subtitles. Compared with an SMT baseline system, experimental results show that our approach achieves a significant improvement of +1.58 BLEU points in translation performance with 66% F-score for DP generation accuracy for Chinese-English, and nearly +1 BLEU point with 58% F-score for Japanese-English. We believe that this work could help both MT researchers and industries to boost the performance of MT systems between pro-drop and non-pro-drop languages.

show abstract

“…The difficulties in projection can be mainly divided into two categories: word alignment errors and annotation criterion difference (Ganchev et al 2009). …”

Section: Projection For Improving Parsing Accuracymentioning

confidence: 99%

Constrained Partial Parsing Based Dependency Tree Projection for Tree-to-Tree Machine Translation

Chu

Shen

Cromierès

et al. 2017

Journal of Natural Language Processing

View full text Add to dashboard Cite

Ideally, tree-to-tree machine translation (MT) that utilizes syntactic parse trees on both source and target sides could preserve non-local structure, and thus generate fluent and accurate translations. In practice, however, firstly, high quality parsers for both source and target languages are difficult to obtain; secondly, even if we have high quality parsers on both sides, they still can be non-isomorphic because of the annotation criterion difference between the two languages. The lack of isomorphism between the parse trees makes it difficult to extract translation rules. This extremely limits the performance of tree-to-tree MT. In this article, we present an approach that projects dependency parse trees from the language side that has a high quality parser, to the side that has a low quality parser, to improve the isomorphism of the parse trees. We first project a part of the dependencies with high confidence to make a partial parse tree, and then complement the remaining dependencies with partial parsing constrained by the already projected dependencies. Experiments conducted on the Japanese-Chinese and English-Chinese language pairs show that our proposed method significantly improves the performance on both the two language pairs.

show abstract

Dependency grammar induction via bitext projection constraints

Cited by 68 publications

References 23 publications

Unsupervised Dependency Parsing with Transferring Distribution via Parallel Guidance and Entropy Regularization

Unsupervised Dependency Parsing with Transferring Distribution via Parallel Guidance and Entropy Regularization

A novel and robust approach for pro-drop language translation

Constrained Partial Parsing Based Dependency Tree Projection for Tree-to-Tree Machine Translation

Contact Info

Product

Resources

About