scholarly journals Joint POS Tagging and Transition-based Constituent Parsing in Chinese with Non-local Features

2014 ◽  
Author(s):  
Zhiguo Wang ◽  
Nianwen Xue
Keyword(s):  
Local Features ◽  
Pos Tagging ◽  
Non Local

LNPSS: SAR image despeckling based on local and non-local features using patch shape selection and edges linking

Measurement ◽  
2020 ◽  
Vol 164 ◽  
pp. 107989
Author(s):  
Ramin Ranjbarzadeh ◽  
Soroush Baseri Saadi ◽  
Amir Amirabadi
Keyword(s):  
Local Features ◽  
Sar Image ◽  
Patch Shape ◽  
Shape Selection ◽  
Non Local ◽  
Image Despeckling

scholarly journals An underspecification approach to Hausa resumption

2016 ◽  
Author(s):  
Berthold Crysmann
Keyword(s):  
Recent Work ◽  
Local Features ◽  
Division Of Labour ◽  
Single Feature ◽  
Pronoun Use ◽  
Non Local ◽  
Unbounded Dependency ◽  
The Difference ◽  
Treat All

Within recent work on the treatment of resumption in HPSG, there is growing consensus that resumptive unbounded dependency constructions (=UDCs) should be modelled on a par with gap-type UDCs (Alotaibi and Borsley, 2013; Borsley, 2010; Crysmann, 2012b; Taghvaipour, 2005), using a single feature for both types of dependencies, rather than separate features, as proposed by Vaillette (2001a,b). Yet, authors disagree as to where exactly in the grammar the resumptive function of pronominals should be established: while Crysmann (2012b, 2015) advances an ambiguity approach that has pronominal synsem objects being ambiguous between a resumptive and an ordinary pronoun use, Borsley (2010); Alotaibi and Borsley (2013), by contrast, treat all pronominals, resumptive or not, as ordinary pronouns and effect their resumptive use by means of tailoring the amalgamation principle to potentially include pronominal indices. While their decision provides a straightforward account of McCloskey’s generalisation that resumptives always look like the ordinary pronouns of the language, it fails to capture the difference in semantics between ordinary pronominal and resumptive uses. In this paper, I shall reexamine the evidence from Hausa and propose to synthesise the approaches put forth by Alotaibi and Borsley (2013) and Crysmann (2012b), and propose that the potential for pronominal and resumptive function (including their difference w.r.t. semantics and non-local features) is captured by means of underspecification, yet the decision as to canonical vs. non-canonical use is made at the level of the governing head (Borsley, 2010; Alotaibi and Borsley, 2013). I shall argue that this division of labour is sufficient to derive the correct gap-like semantics for resumptives, maintains standard deterministic amalgamation, and, finally, provides an answer to McCloskey’s generalisation.

Leveraging GANs via Non-local Features

2021 ◽  
pp. 551-562
Author(s):  
Xuyang Peng ◽  
Weifeng Liu ◽  
Baodi Liu ◽  
Kai Zhang ◽  
Xiaoping Lu ◽  
...  
Keyword(s):  
Local Features ◽  
Non Local

scholarly journals Branch and Bound Algorithm for Dependency Parsing with Non-local Features

2013 ◽  
Vol 1 ◽  
pp. 37-48 ◽  
Author(s):  
Xian Qian ◽  
Yang Liu
Keyword(s):  
Dynamic Programming ◽  
Computational Complexity ◽  
Branch And Bound ◽  
Graphical Models ◽  
Upper Bound ◽  
Local Features ◽  
Dependency Parsing ◽  
Non Local ◽  
Efficient Decoding ◽  
High Computational Complexity

Graph based dependency parsing is inefficient when handling non-local features due to high computational complexity of inference. In this paper, we proposed an exact and efficient decoding algorithm based on the Branch and Bound (B&B) framework where non-local features are bounded by a linear combination of local features. Dynamic programming is used to search the upper bound. Experiments are conducted on English PTB and Chinese CTB datasets. We achieved competitive Unlabeled Attachment Score (UAS) when no additional resources are available: 93.17% for English and 87.25% for Chinese. Parsing speed is 177 words per second for English and 97 words per second for Chinese. Our algorithm is general and can be adapted to non-projective dependency parsing or other graphical models.

Single-Image Real-Time Rain Removal Based on Depth-Guided Non-Local Features

2021 ◽  
pp. 1-1
Author(s):  
Xiaowei Hu ◽  
Lei Zhu ◽  
Tianyu Wang ◽  
Chi-Wing Fu ◽  
Pheng-Ann Heng
Keyword(s):  
Real Time ◽  
Local Features ◽  
Single Image ◽  
Rain Removal ◽  
Non Local
Sign in / Sign up

Export Citation Format

Share Document