scholarly journals Fast and Accurate Neural CRF Constituency Parsing

2020 ◽  
Author(s):  
Yu Zhang ◽  
Houquan Zhou ◽  
Zhenghua Li
Keyword(s):  
Recent Progress ◽  
State Of The Art ◽  
Linear Chain ◽  
Back Propagation ◽  
Boundary Representation ◽  
Two Stage ◽  
The Core ◽  
Gradient Computation ◽  
Core Issues ◽  
New Scoring

Estimating probability distribution is one of the core issues in the NLP field. However, in both deep learning (DL) and pre-DL eras, unlike the vast applications of linear-chain CRF in sequence labeling tasks, very few works have applied tree-structure CRF to constituency parsing, mainly due to the complexity and inefficiency of the inside-outside algorithm. This work presents a fast and accurate neural CRF constituency parser. The key idea is to batchify the inside algorithm for loss computation by direct large tensor operations on GPU, and meanwhile avoid the outside algorithm for gradient computation via efficient back-propagation. We also propose a simple two-stage bracketing-then-labeling parsing approach to improve efficiency further. To improve the parsing performance, inspired by recent progress in dependency parsing, we introduce a new scoring architecture based on boundary representation and biaffine attention, and a beneficial dropout strategy. Experiments on PTB, CTB5.1, and CTB7 show that our two-stage CRF parser achieves new state-of-the-art performance on both settings of w/o and w/ BERT, and can parse over 1,000 sentences per second. We release our code at https://github.com/yzhangcs/crfpar.

scholarly journals Multiobjective multitasking optimization assisted by multidirectional prediction method

2022 ◽  
Author(s):  
Qianlong Dang ◽  
Weifeng Gao ◽  
Maoguo Gong
Keyword(s):  
State Of The Art ◽  
Prediction Method ◽  
Research Topic ◽  
Representative Point ◽  
The Core ◽  
Multiple Prediction ◽  
Representative Points ◽  
Core Issues ◽  
Adaptation Method ◽  
Efficient Transfer

AbstractMultiobjective multitasking optimization (MTO) is an emerging research topic in the field of evolutionary computation, which has attracted extensive attention, and many evolutionary multitasking (EMT) algorithms have been proposed. One of the core issues, designing an efficient transfer strategy, has been scarcely explored. Keeping this in mind, this paper is the first attempt to design an efficient transfer strategy based on multidirectional prediction method. Specifically, the population is divided into multiple classes by the binary clustering method, and the representative point of each class is calculated. Then, an effective prediction direction method is developed to generate multiple prediction directions by representative points. Afterward, a mutation strength adaptation method is proposed according to the improvement degree of each class. Finally, the predictive transferred solutions are generated as transfer knowledge by the prediction directions and mutation strengths. By the above process, a multiobjective EMT algorithm based on multidirectional prediction method is presented. Experiments on two MTO test suits indicate that the proposed algorithm is effective and competitive to other state-of-the-art EMT algorithms.

scholarly journals Image Restoration by Learning Morphological Opening-Closing Network

2020 ◽  
Vol 4 (1) ◽  
pp. 87-107
Author(s):  
Ranjan Mondal ◽  
Moni Shankar Dey ◽  
Bhabatosh Chanda
Keyword(s):  
Neural Network ◽  
Image Restoration ◽  
State Of The Art ◽  
Source Code ◽  
Back Propagation ◽  
Image Features ◽  
Main Difficulty ◽  
The Right ◽  
Right Order ◽  
Morphological Opening

AbstractMathematical morphology is a powerful tool for image processing tasks. The main difficulty in designing mathematical morphological algorithm is deciding the order of operators/filters and the corresponding structuring elements (SEs). In this work, we develop morphological network composed of alternate sequences of dilation and erosion layers, which depending on learned SEs, may form opening or closing layers. These layers in the right order along with linear combination (of their outputs) are useful in extracting image features and processing them. Structuring elements in the network are learned by back-propagation method guided by minimization of the loss function. Efficacy of the proposed network is established by applying it to two interesting image restoration problems, namely de-raining and de-hazing. Results are comparable to that of many state-of-the-art algorithms for most of the images. It is also worth mentioning that the number of network parameters to handle is much less than that of popular convolutional neural network for similar tasks. The source code can be found here https://github.com/ranjanZ/Mophological-Opening-Closing-Net

“Leaving No One Behind” as a Site of Contestation and Reinterpretation

2018 ◽  
Vol 9 (2) ◽  
Author(s):  
Sakiko Fukuda-Parr ◽  
Thea Smaavik Hegstad
Keyword(s):  
Social Protection ◽  
Inclusive Development ◽  
Vulnerable Groups ◽  
Transformative Change ◽  
The Core ◽  
2030 Agenda ◽  
Social Opportunities ◽  
A Site ◽  
Core Issues ◽  
Distribution Of Income

Abstract One of the most important elements of the 2030 Agenda and the SDGs is the strong commitment to inclusive development, and “leaving no one behind” has emerged as a central theme of the agenda. How did this consensus come about? And what does this term mean and how is it being interpreted? This matters because SDGs shift international norms. Global goals exert influence on policy and action of governments and stakeholders in development operates through discourse. So the language used in formulating the UN Agenda is a terrain of active contestation. This paper aims to explain the politics that led to this term as a core theme. It argues that LNOB was promoted to frame the SDG inequality agenda as inclusive development, focusing on the exclusion of marginalized and vulnerable groups from social opportunities, deflecting attention from the core issues of distribution of income and wealth, and the challenge of “extreme inequality.” The term is adequately vague so as to accommodate wide ranging interpretations. Through a content analysis of LNOB in 43 VNRs, the paper finds that the majority of country strategies identify LNOB as priority to the very poor, and identify it with a strategy for social protection. This narrow interpretation does not respond to the ambition of the 2030 Agenda for transformative change, and the principles of human rights approaches laid out.

Equality and Equity in Chinese Higher Education in the Post-massification Era: An Analysis Based on Chinese Scholarly Literature

2021 ◽  
pp. 1-22
Author(s):  
Qiang Zha
Keyword(s):  
Higher Education ◽  
Literature Review ◽  
Bibliometric Analysis ◽  
Chinese Higher Education ◽  
Scholarly Literature ◽  
The Core ◽  
Research Questions ◽  
Changes Over Time ◽  
Core Issues ◽  
Over Time

Abstract This paper examines several research questions relating to equality and equity in Chinese higher education via an extended literature review, which in turn sheds light on evolving scholarly explorations into this theme. First, in the post-massification era, has the Chinese situation of equality and equity in higher education improved or deteriorated since the late 1990s? Second, what are the core issues with respect to equality and equity in Chinese higher education? Third, how have those core issues evolved or changed over time and what does the evolution indicate and entail? Methodologically, this paper uses a bibliometric analysis to detect the topical hotspots in scholarly literature and their changes over time. The study then investigates each of those topical terrains against their temporal contexts in order to gain insights into the core issues.

scholarly journals Solid-state nanopore systems: from materials to applications

2021 ◽  
Vol 13 (1) ◽  
Author(s):  
Yuhui He ◽  
Makusu Tsutsui ◽  
Yue Zhou ◽  
Xiang-Shui Miao
Keyword(s):  
Solid State ◽  
Recent Progress ◽  
State Of The Art ◽  
Ion Selectivity ◽  
Dna Origami ◽  
Fundamental Interest ◽  
Reverse Electrodialysis ◽  
Promising Application ◽  
Flow Through ◽  
Wall Materials

AbstractIon transport and hydrodynamic flow through nanometer-sized channels (nanopores) have been increasingly studied owing to not only the fundamental interest in the abundance of novel phenomena that has been observed but also their promising application in innovative nanodevices, including next-generation sequencers, nanopower generators, and memristive synapses. We first review various kinds of materials and the associated state-of-the-art processes developed for fabricating nanoscale pores, including the emerging structures of DNA origami and 2-dimensional nanopores. Then, the unique transport phenomena are examined wherein the surface properties of wall materials play predominant roles in inducing intriguing characteristics, such as ion selectivity and reverse electrodialysis. Finally, we highlight recent progress in the potential application of nanopores, ranging from their use in biosensors to nanopore-based artificial synapses.

scholarly journals Representing Deep Neural Networks Latent Space Geometries with Graphs

Algorithms ◽  
2021 ◽  
Vol 14 (2) ◽  
pp. 39
Author(s):  
Carlos Lassance ◽  
Vincent Gripon ◽  
Antonio Ortega
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Deep Learning ◽  
Objective Function ◽  
Learning Process ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
The Core ◽  
Learning Tasks ◽  
Latent Space

Deep Learning (DL) has attracted a lot of attention for its ability to reach state-of-the-art performance in many machine learning tasks. The core principle of DL methods consists of training composite architectures in an end-to-end fashion, where inputs are associated with outputs trained to optimize an objective function. Because of their compositional nature, DL architectures naturally exhibit several intermediate representations of the inputs, which belong to so-called latent spaces. When treated individually, these intermediate representations are most of the time unconstrained during the learning process, as it is unclear which properties should be favored. However, when processing a batch of inputs concurrently, the corresponding set of intermediate representations exhibit relations (what we call a geometry) on which desired properties can be sought. In this work, we show that it is possible to introduce constraints on these latent geometries to address various problems. In more detail, we propose to represent geometries by constructing similarity graphs from the intermediate representations obtained when processing a batch of inputs. By constraining these Latent Geometry Graphs (LGGs), we address the three following problems: (i) reproducing the behavior of a teacher architecture is achieved by mimicking its geometry, (ii) designing efficient embeddings for classification is achieved by targeting specific geometries, and (iii) robustness to deviations on inputs is achieved via enforcing smooth variation of geometry between consecutive latent spaces. Using standard vision benchmarks, we demonstrate the ability of the proposed geometry-based methods in solving the considered problems.

scholarly journals Knowing What, How and Why: A Near Complete Solution for Aspect-Based Sentiment Analysis

2020 ◽  
Vol 34 (05) ◽  
pp. 8600-8607
Author(s):  
Haiyun Peng ◽  
Lu Xu ◽  
Lidong Bing ◽  
Fei Huang ◽  
Wei Lu ◽  
...  
Keyword(s):  
Sentiment Analysis ◽  
State Of The Art ◽  
Complete Solution ◽  
Unified Model ◽  
Two Stage ◽  
Fine Grained ◽  
Aspect Extraction ◽  
Second Stage ◽  
Opinion Extraction ◽  
Complete Story

Target-based sentiment analysis or aspect-based sentiment analysis (ABSA) refers to addressing various sentiment analysis tasks at a fine-grained level, which includes but is not limited to aspect extraction, aspect sentiment classification, and opinion extraction. There exist many solvers of the above individual subtasks or a combination of two subtasks, and they can work together to tell a complete story, i.e. the discussed aspect, the sentiment on it, and the cause of the sentiment. However, no previous ABSA research tried to provide a complete solution in one shot. In this paper, we introduce a new subtask under ABSA, named aspect sentiment triplet extraction (ASTE). Particularly, a solver of this task needs to extract triplets (What, How, Why) from the inputs, which show WHAT the targeted aspects are, HOW their sentiment polarities are and WHY they have such polarities (i.e. opinion reasons). For instance, one triplet from “Waiters are very friendly and the pasta is simply average” could be (‘Waiters’, positive, ‘friendly’). We propose a two-stage framework to address this task. The first stage predicts what, how and why in a unified model, and then the second stage pairs up the predicted what (how) and why from the first stage to output triplets. In the experiments, our framework has set a benchmark performance in this novel triplet extraction task. Meanwhile, it outperforms a few strong baselines adapted from state-of-the-art related methods.

Genealogy of Colonial Discourse: Hindu Traditions and the Limits of European Representation

2009 ◽  
Vol 51 (3) ◽  
pp. 563-589 ◽  
Author(s):  
Raf Gelders
Keyword(s):  
Nineteenth Century ◽  
South Asian ◽  
Colonial Discourse ◽  
Colonial State ◽  
The Core ◽  
European Culture ◽  
Eastern Cultures ◽  
The Subject ◽  
Core Issues

In the aftermath of Edward Said's Orientalism (1978), European representations of Eastern cultures have returned to preoccupy the Western academy. Much of this work reiterates the point that nineteenth-century Orientalist scholarship was a corpus of knowledge that was implicated in and reinforced colonial state formation in India. The pivotal role of native informants in the production of colonial discourse and its subsequent use in servicing the material adjuncts of the colonial state notwithstanding, there has been some recognition in South Asian scholarship of the moot point that the colonial constructs themselves built upon an existing, precolonial European discourse on India and its indigenous culture. However, there is as yet little scholarly consensus or indeed literature on the core issues of how and when these edifices came to be formed, or the intellectual and cultural axes they drew from. This genealogy of colonial discourse is the subject of this essay. Its principal concerns are the formalization of a conceptual unit in the sixteenth and seventeenth centuries, called “Hinduism” today, and the larger reality of European culture and religion that shaped the contours of representation.

Sign in / Sign up

Export Citation Format

Share Document