Filters








24,611 Hits in 3.3 sec

Advances in discriminative parsing

Joseph Turian, I. Dan Melamed
2006 Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL - ACL '06  
The present work advances the accuracy and training speed of discriminative parsing.  ...  Our discriminative parsing method has no generative component, yet surpasses a generative baseline on constituent parsing, and does so with minimal linguistic cleverness.  ...  Conclusion Our work has made advances in both accuracy and training speed of discriminative parsing.  ... 
doi:10.3115/1220175.1220285 dblp:conf/acl/TurianM06 fatcat:7q5zhbmxw5fqlncglmqsqsvb6u

Page 67 of Computational Linguistics Vol. 31, Issue 1 [page]

2005 Computational Linguistics  
Chapter Discriminative Reranking for NLP In Advances in Neural Information Processing Systems (NIPS 14), Vancouver. Collins, Michael, and Nigel Duffy. 2002.  ...  In Advances in Neural Information Processing Systems (NIPS 12), Denver. Freund, Yoav, Raj lyer, and Yoram Singer. 1999, Robert E. Schapire, 1998.  ... 

Page 349 of Computational Linguistics Vol. 21, Issue 3 [page]

1995 Computational Linguistics  
“GLR parsing with probability.” In Generalized LR Parsing, edited by Masaru Tomita, 113-128. Kluwer Academic Publisher.  ...  “A sequential truncation parsing algorithm based on the score function.” In Proceedings of 1989 International Workshop on Parsing Technologies (IWPT-89). Pittsburgh, 95-104. Wright, J.  ... 

A Survey of Unsupervised Dependency Parsing [article]

Wenjuan Han, Yong Jiang, Hwee Tou Ng, Kewei Tu
2020 arXiv   pre-print
Syntactic dependency parsing is an important task in natural language processing.  ...  It also serves as the basis for other research in low-resource parsing.  ...  Conclusion In this paper, we present a survey on the current advances of unsupervised dependency parsing.  ... 
arXiv:2010.01535v1 fatcat:4wd4dgducnbeti6kukpmfw5r4i

Combining discriminative re-ranking and co-training for parsing Mandarin speech transcripts

Wen Wang
2009 2009 IEEE International Conference on Acoustics, Speech and Signal Processing  
Discriminative reranking has been able to significantly improve parsing performance, and co-training has proven to be an effective weakly supervised learning algorithm to bootstrap parsers from a small  ...  In this paper, we present systematic investigations on combining discriminative reranking and co-training, including co-training reranked parsers and co-training rerankers.  ...  The authors thank Mary Harper and Zhongqiang Huang for discussions on Chinese parsing and discriminative reranking.  ... 
doi:10.1109/icassp.2009.4960681 dblp:conf/icassp/Wang09 fatcat:jnzwnbjqtvdpxe4oaef7qqlira

Recent Advances in Dependency Parsing

Qin Iris Wang, Yue Zhang
2010 North American Chapter of the Association for Computational Linguistics  
Data-driven (statistical) approaches have been playing an increasingly prominent role in parsing since the 1990s.  ...  In recent years, there has been a growing interest in dependency-based as opposed to constituency-based approaches to syntactic parsing, with application to a wide range of research areas and different  ...  More specifically, his research area is the syntactic analysis of the Chinese language, using discriminative machine-learning approaches.  ... 
dblp:conf/naacl/WangZ10 fatcat:ydgdprir55acxfthxqs5bnquvq

Discriminative Log-Linear Grammars with Latent Variables

Slav Petrov, Dan Klein
2007 Neural Information Processing Systems  
On full-scale treebank parsing experiments, the discriminative latent models outperform both the comparable generative latent models as well as the discriminative non-latent baselines.  ...  Central to efficient discriminative training is a hierarchical pruning procedure which allows feature expectations to be efficiently approximated in a gradient-based procedure.  ...  Even with recent advances in parsing efficiency and fast CPUs, parsing the entire corpus repeatedly remains prohibitive.  ... 
dblp:conf/nips/PetrovK07 fatcat:sw2dimtpjvgy3jbwswwnl3ncdu

Efficient, Feature-based, Conditional Random Field Parsing

Jenny Rose Finkel, Alex Kleeman, Christopher D. Manning
2008 Annual Meeting of the Association for Computational Linguistics  
Discriminative feature-based methods are widely used in natural language processing, but sentence parsing is still dominated by generative methods.  ...  a conditional random field model, which has been successfully scaled to the full WSJ parsing data.  ...  This paper is based on work funded in part by the Defense Advanced Research Projects Agency through IBM, by the Disruptive Technology Office (DTO) Phase III Program for Advanced Question Answering for  ... 
dblp:conf/acl/FinkelKM08 fatcat:ce7qzmlrebbghmyi44vnoniqme

Focusing on Persons: Colorizing Old Images Learning from Modern Historical Movies [article]

Xin Jin, Zhonglan Li, Ke Liu, Dongqing Zou, Xiaodong Li, Xingfan Zhu, Ziyin Zhou, Qilong Sun, Qingyu Liu
2021 arXiv   pre-print
In this paper, a HistoryNet including three parts, namely, classification, fine grained semantic parsing and colorization, is proposed.  ...  In the training process, we integrate classification and semantic parsing features into the coloring generation network to improve colorization.  ...  This work is partially supported by the National Natural Science Foundation of China (62072014), the Beijing Natural Science Foundation (L192040), and the Advanced Discipline Construction Project of Beijing  ... 
arXiv:2108.06515v1 fatcat:7srb4hqobzfkhif2qpge7jptsm

CPGAN: Full-Spectrum Content-Parsing Generative Adversarial Networks for Text-to-Image Synthesis [article]

Jiadong Liang and Wenjie Pei and Feng Lu
2020 arXiv   pre-print
Meanwhile, the synthesized image is parsed to learn its semantics in an object-aware manner.  ...  Extensive experiments on COCO dataset manifest that our model advances the state-of-the-art performance significantly (from 35.69 to 52.73 in Inception Score).  ...  Nevertheless, OAIE still advances the performances after being mounted over the single FGCD or MATE + FGCD.  ... 
arXiv:1912.08562v2 fatcat:xmc5jqrkuvbp3hfviqbqvrz57q

Macro-Micro Adversarial Network for Human Parsing [article]

Yawei Luo, Zhedong Zheng, Liang Zheng, Tao Guan, Junqing Yu, Yi Yang
2018 arXiv   pre-print
In our experiment, we validate that the two discriminators are complementary to each other in improving the human parsing accuracy.  ...  In human parsing, the pixel-wise classification loss has drawbacks in its low-level local inconsistency and high-level semantic inconsistency.  ...  Recent advances in human parsing and semantic segmentation [19, 34, 10, 23, 37, 36] mostly explore the potential of the convolutional neural network (CNN).  ... 
arXiv:1807.08260v2 fatcat:snra4b73tfdblfyor5rebajiri

Macro-Micro Adversarial Network for Human Parsing [chapter]

Yawei Luo, Zhedong Zheng, Liang Zheng, Tao Guan, Junqing Yu, Yi Yang
2018 Lecture Notes in Computer Science  
In our experiment, we validate that the two discriminators are complementary to each other in improving the human parsing accuracy.  ...  In human parsing, the pixel-wise classification loss has drawbacks in its low-level local inconsistency and high-level semantic inconsistency.  ...  Recent advances in human parsing and semantic segmentation [19, 34, 10, 23, 37, 36] mostly explore the potential of the convolutional neural network (CNN).  ... 
doi:10.1007/978-3-030-01240-3_26 fatcat:n7gk56e2sjcqbprl2celnaorzu

Generating LR(1) parsers of small size [chapter]

Fortes Gálvez José
1992 Lecture Notes in Computer Science  
Results from an experimental implementation of the parser generator show important reductions in automaton size in comparison with standard LR methods.  ...  Classic LR(1) parsing methods have the problem of producing too large parsing tables for programming language grammars.  ...  A partial solution is given by bounded-context methods [4, 6, 11] , in which a deeper--although limited in advance search in the stack is made.  ... 
doi:10.1007/3-540-55984-1_2 fatcat:rk6pctytsrg6xd7vznwmezyqey

Page 475 of Computational Linguistics Vol. 33, Issue 4 [page]

2007 Computational Linguistics  
In Proceedings of the Third Workshop on Very Large Corpora, pages 27-38, Somerset, NJ. Collins, Michael and Terry Koo. 2005. Discriminative reranking for natural language parsing.  ...  Coarse-to-fine n-best parsing and MaxEnt discriminative reranking. In Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL) pages 173-180, Ann Arbor, MI.  ... 

Heavy Rain Face Image Restoration: Integrating Physical Degradation Model and Facial Component-Guided Adversarial Learning

Chang-Hwan Son, Da-Hee Jeong
2022 Sensors  
To focus on informative facial features and reinforce the authenticity of facial components, such as the eyes and nose, a face parsing-guided generator and facial local discriminators are designed for  ...  For example, in heavy rain, face images captured by CCTV from a distance have significant deterioration in both visibility and resolution.  ...  As mentioned in Section 3.5, the SRGAN framework was adopted for the SR module in the proposed network. Therefore, the proposed FCG-GAN can be considered an advanced SRGAN.  ... 
doi:10.3390/s22145359 pmid:35891041 pmcid:PMC9319128 fatcat:xhwnpafgvzebxmcjdebobzr7z4
« Previous Showing results 1 — 15 out of 24,611 results