Filters








80 Hits in 3.9 sec

Dependency grammar induction via bitext projection constraints

Kuzman Ganchev, Jennifer Gillenwater, Ben Taskar
2009 Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 1 - ACL-IJCNLP '09   unpublished
The wide availability of parallel text and accurate parsers in English has opened up the possibility of grammar induction through partial transfer across bitext.  ...  We consider generative and discriminative models for dependency grammar induction that use word-level alignments and a source language parser (English) to constrain the space of possible target trees.  ...  The prob-(a) (b) Figure 1 : (a) Overview of our grammar induction approach via bitext: the source (English) is parsed and word-aligned with target; after filtering, projected dependencies define constraints  ... 
doi:10.3115/1687878.1687931 fatcat:atnjaxa44jb3bezkfeku57vorm

Soft Cross-lingual Syntax Projection for Dependency Parsing

Zhenghua Li, Min Zhang, Wenliang Chen
2014 International Conference on Computational Linguistics  
For a word that has no head words after projection, we enrich the projected structure with all other words as its candidate heads as long as the newly-added dependency does not cross any projected dependencies  ...  Here, soft means that we only project reliable dependencies to compose high-quality target structures.  ...  Previous work on syntax projection mostly focuses on unsupervised grammar induction where no labeled data exists for target language (Hwa et al., 2005; Spreyer and Kuhn, 2009; Ganchev et al., 2009; .  ... 
dblp:conf/coling/Li0C14 fatcat:7ed3scnmv5czros3k2z3ne3b6e

Bilingually-Guided Monolingual Dependency Grammar Induction

Kai Liu, Yajuan Lü, Wenbin Jiang, Qun Liu
2013 Annual Meeting of the Association for Computational Linguistics  
This paper describes a novel strategy for automatic induction of a monolingual dependency grammar under the guidance of bilingually-projected dependency.  ...  integrates the advantages of bilingual projection and unsupervised induction, so as to induce a monolingual grammar much better than previous models only using bilingual projection or unsupervised induction  ...  So we extract projected discrete dependency arc instances instead of treebank as training set for the projected grammar induction model.  ... 
dblp:conf/acl/LiuLJL13 fatcat:tbtxczyzarbn3pu3grzhkonpl4

Phylogenetic Grammar Induction

Taylor Berg-Kirkpatrick, Dan Klein
2010 Annual Meeting of the Association for Computational Linguistics  
We present an approach to multilingual grammar induction that exploits a phylogeny-structured model of parameter drift. Our method does not require any translated texts or token-level alignments.  ...  Joint induction in the multilingual model substantially outperforms independent learning, with larger gains both from more articulated phylogenies and as well as from increasing numbers of languages.  ...  Acknowledgements This project is funded in part by the NSF under grant 0915265 and DARPA under grant N10AP20007.  ... 
dblp:conf/acl/Berg-KirkpatrickK10 fatcat:5teitgknfzfj5dh56nripdxjoy

Cross-lingual Pseudo-Projected Expectation Regularization for Weakly Supervised Learning [article]

Mengqiu Wang, Christopher D. Manning
2013 arXiv   pre-print
Past approaches project labels across bitext and use them as features or gold labels for training.  ...  We consider a multilingual weakly supervised learning scenario where knowledge from annotated corpora in a resource-rich language is transferred via bitext to guide the learning in other languages.  ...  As a result, bitext has been effectively utilized for unsupervised multilingual grammar induction (Alshawi et al., 2000; , parsing (Burkett and Klein, 2008) , and sequence labeling .  ... 
arXiv:1310.1597v1 fatcat:q4g3kudjhvcthkrwhzcmeuu2ku

Cross-lingual Projected Expectation Regularization for Weakly Supervised Learning

Mengqiu Wang, Christopher D. Manning
2014 Transactions of the Association for Computational Linguistics  
Past approaches project labels across bitext and use them as features or gold labels for training.  ...  We consider a multilingual weakly supervised learning scenario where knowledge from annotated corpora in a resource-rich language is transferred via bitext to guide the learning in other languages.  ...  Defense Advanced Research Projects Agency (DARPA) Broad Operational Language Translation (BOLT) program through IBM.  ... 
doi:10.1162/tacl_a_00165 fatcat:j2xxjxjjtvhxbg2aqcs2gejzxq

Towards a Weighted Induction Method of Dependency Annotation [chapter]

Alina Wróblewska, Adam Przepiórkowski
2014 Lecture Notes in Computer Science  
relations (weighted induction).  ...  However, we involve a weighting factor not only in the process of projecting dependency relations (weighted projection) but also in the process of acquiring dependency trees from projected sets of dependency  ...  For this reason, intensive research has been conducted on unsupervised grammar induction.  ... 
doi:10.1007/978-3-319-10888-9_17 fatcat:fhqoevpxyzexdhia4y22vz6d4e

Max-Margin Synchronous Grammar Induction for Machine Translation

Xinyan Xiao, Deyi Xiong
2013 Conference on Empirical Methods in Natural Language Processing  
Traditional synchronous grammar induction estimates parameters by maximizing likelihood, which only has a loose relation to translation quality.  ...  Alternatively, we propose a max-margin estimation approach to discriminatively inducing synchronous grammars for machine translation, which directly optimizes translation quality measured by BLEU.  ...  Acknowledgments The first author was partially supported by 863 State Key Project (No. 2011AA01A207) and National Key Technology R&D Program (No. 2012BAH39B03).  ... 
dblp:conf/emnlp/XiaoX13 fatcat:behu5l6oprg7rdetprjamgsoia

Three Dependency-and-Boundary Models for Grammar Induction

Valentin I. Spitkovsky, Hiyan Alshawi, Daniel Jurafsky
2012 Conference on Empirical Methods in Natural Language Processing  
Our models induce state-of-the-art dependency grammars for many languages without special knowledge of optimal input sentence lengths or biased, manually-tuned initializers.  ...  We build on three intuitions that are explicit in phrase-structure grammars but only implicit in standard dependency formulations: (i) Distributions of words that occur at sentence boundaries -such as  ...  Funded, in part, by Defense Advanced Research Projects Agency (DARPA) Machine Reading Program, under Air Force Research Laboratory (AFRL) prime contract no. FA8750-09-C-0181.  ... 
dblp:conf/emnlp/SpitkovskyAJ12 fatcat:l7s2sc5c6rh3ff2chejpqzbkdq

Sequence-to-Sequence Learning with Latent Neural Grammars [article]

Yoon Kim
2021 arXiv   pre-print
We develop a neural parameterization of the grammar which enables parameter sharing over the combinatorial space of derivation rules without the need for manual feature engineering.  ...  This work explores an alternative, hierarchical approach to sequence-to-sequence learning with quasi-synchronous grammars, where each node in the target tree is transduced by a node in the source tree.  ...  We have shown that the formalism quasi-synchronous grammars provides a flexible tool with which to imbue inductive biases, operationalize constraints, and interface with the model.  ... 
arXiv:2109.01135v7 fatcat:x6rc3nttz5c4jczie27vpdifdm

Cross-lingual Dependency Parsing Based on Distributed Representations

Jiang Guo, Wanxiang Che, David Yarowsky, Haifeng Wang, Ting Liu
2015 Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)  
It also significantly outperforms McDonald et al. (2013) augmented with projected cluster features on identical data.  ...  This paper investigates the problem of cross-lingual dependency parsing, aiming at inducing dependency parsers for low-resource languages while using only training data from a resource-rich language (e.g  ...  This work was supported by the National Key Basic Research Program of China via grant 2014CB340503 and the National Natural Science Foundation of China (NSFC) via grant 61133012 and 61370164.  ... 
doi:10.3115/v1/p15-1119 dblp:conf/acl/GuoCYWL15 fatcat:iknfii6zdzeb7dsem4nephyrpu

Training Dependency Parsers with Partial Annotation [article]

Zhenghua Li, Yue Zhang, Jiayuan Chao, Min Zhang
2016 arXiv   pre-print
We conduct extensive experiments on Penn Treebank under three different settings for simulating PA, i.e., random dependencies, most uncertain dependencies, and dependencies with divergent outputs from  ...  Taking dependency parsing as our case study, this paper describes and compares two straightforward approaches for three mainstream dependency parsers.  ...  This setting may be best fit the scenario automatic syntax projection based on bitext, where the projected dependencies tend to be arbitrary (and noisy) due to the errors in automatic source-language parses  ... 
arXiv:1609.09247v1 fatcat:woniiy5svrfotauhf3lgv2onkm

Synthetic Treebanking for Cross-Lingual Dependency Parsing

Jörg Tiedemann, Zeljko Agić
2016 The Journal of Artificial Intelligence Research  
We emphasize synthetic treebanking: the automatic creation of target language treebanks by means of annotation projection and machine translation.  ...  We present competitive results in cross-lingual dependency parsing using a combination of various techniques that contribute to the overall success of the method.  ...  Figure 2 illustrates the general idea of annotation projection for the case of syntactic dependencies and parser model induction.  ... 
doi:10.1613/jair.4785 fatcat:roo7hsonqzfpfpuiwqid7oc3kq

Phrase Dependency Machine Translation with Quasi-Synchronous Tree-to-Tree Features

Kevin Gimpel, Noah A. Smith
2014 Computational Linguistics  
Smith and Eisner (2006) introduced quasi-synchronous grammar, a formalism that treats non-isomorphic structure softly using features rather than hard constraints.  ...  In this article, we present a tree-to-tree machine translation system inspired by quasi-synchronous grammar.  ...  These algorithms can be used to sample projective dependency trees by representing a projective dependency grammar using a context-free grammar (Smith 2006; Johnson 2007) .  ... 
doi:10.1162/coli_a_00175 fatcat:e3hfi5iovvdrrhqbi76h3yrvwq

Dependency Parsing with Partial Annotations: An Empirical Comparison

Yue Zhang, Zhenghua Li, Jun Lang, Qingrong Xia, Min Zhang
2017 International Joint Conference on Natural Language Processing  
This paper describes and compares two straightforward approaches for dependency parsing with partial annotations (PA).  ...  This setting may be best fit the scenario automatic syntax projection based on bitext, where the projected dependencies tend to be arbitrary (and noisy) due to the errors in automatic source-language parses  ...  Hwa (1999) pioneers the idea of exploring PA for constituent grammar induction based on a variant Inside-Outside re-estimation algorithm (Pereira and Schabes, 1992) .  ... 
dblp:conf/ijcnlp/ZhangLLXZ17 fatcat:d7wlbonkd5e43koqc5ug2jozza
« Previous Showing results 1 — 15 out of 80 results