scholarly journals Semantic Specialization of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints

2017 ◽  
Vol 5 ◽  
pp. 309-324 ◽  
Author(s):  
Nikola Mrkšić ◽  
Ivan Vulić ◽  
Diarmuid Ó Séaghdha ◽  
Ira Leviant ◽  
Roi Reichart ◽  
...  
Keyword(s):  
State Of The Art ◽  
Vector Spaces ◽  
Lexical Resources ◽  
High Quality ◽  
Performance Improvements ◽  
State Tracking ◽  
Cross Lingual ◽  
Semantic Transfer ◽  
Multiple Languages

We present Attract-Repel, an algorithm for improving the semantic quality of word vectors by injecting constraints extracted from lexical resources. Attract-Repel facilitates the use of constraints from mono- and cross-lingual resources, yielding semantically specialized cross-lingual vector spaces. Our evaluation shows that the method can make use of existing cross-lingual lexicons to construct high-quality vector spaces for a plethora of different languages, facilitating semantic transfer from high- to lower-resource ones. The effectiveness of our approach is demonstrated with state-of-the-art results on semantic similarity datasets in six languages. We next show that Attract-Repel-specialized vectors boost performance in the downstream task of dialogue state tracking (DST) across multiple languages. Finally, we show that cross-lingual vector spaces produced by our algorithm facilitate the training of multilingual DST models, which brings further performance improvements.

UBAR

2021 ◽  
Vol 20 (3) ◽  
pp. 1-25
Author(s):  
Elham Shamsa ◽  
Alma Pröbstl ◽  
Nima TaheriNejad ◽  
Anil Kanduri ◽  
Samarjit Chakraborty ◽  
...  
Keyword(s):  
Resource Management ◽  
Quality Of Experience ◽  
State Of The Art ◽  
State Of Charge ◽  
User Preference ◽  
Management Approach ◽  
High Quality ◽  
Trade Off ◽  
Run Time

Smartphone users require high Battery Cycle Life (BCL) and high Quality of Experience (QoE) during their usage. These two objectives can be conflicting based on the user preference at run-time. Finding the best trade-off between QoE and BCL requires an intelligent resource management approach that considers and learns user preference at run-time. Current approaches focus on one of these two objectives and neglect the other, limiting their efficiency in meeting users’ needs. In this article, we present UBAR, User- and Battery-aware Resource management, which considers dynamic workload, user preference, and user plug-in/out pattern at run-time to provide a suitable trade-off between BCL and QoE. UBAR personalizes this trade-off by learning the user’s habits and using that to satisfy QoE, while considering battery temperature and State of Charge (SOC) pattern to maximize BCL. The evaluation results show that UBAR achieves 10% to 40% improvement compared to the existing state-of-the-art approaches.

Thermal Laser Separation – A Novel Dicing Technology Fulfilling the Demands of Volume Manufacturing of 4H-SiC Devices

2015 ◽  
Vol 821-823 ◽  
pp. 528-532 ◽  
Author(s):  
Dirk Lewke ◽  
Karl Otto Dohnke ◽  
Hans Ulrich Zühlke ◽  
Mercedes Cerezuela Barret ◽  
Martin Schellenberger ◽  
...  
Keyword(s):  
Experimental Data ◽  
Process Control ◽  
Tool Wear ◽  
Large Scale ◽  
State Of The Art ◽  
Scale Production ◽  
High Quality ◽  
Large Scale Production ◽  
Laser Separation

One challenge for volume manufacturing of 4H-SiC devices is the state-of-the-art wafer dicing technology – the mechanical blade dicing which suffers from high tool wear and low feed rates. In this paper we discuss Thermal Laser Separation (TLS) as a novel dicing technology for large scale production of SiC devices. We compare the latest TLS experimental data resulting from fully processed 4H-SiC wafers with results obtained by mechanical dicing technology. Especially typical product relevant features like process control monitoring (PCM) structures and backside metallization, quality of diced SiC-devices as well as productivity are considered. It could be shown that with feed rates up to two orders of magnitude higher than state-of-the-art, no tool wear and high quality of diced chips, TLS has a very promising potential to fulfill the demands of volume manufacturing of 4H-SiC devices.

scholarly journals Dialogue Generation: From Imitation Learning to Inverse Reinforcement Learning

2019 ◽  
Vol 33 ◽  
pp. 6722-6729 ◽  
Author(s):  
Ziming Li ◽  
Julia Kiseleva ◽  
Maarten De Rijke
Keyword(s):  
Reinforcement Learning ◽  
State Of The Art ◽  
The State ◽  
Experimental Results ◽  
Imitation Learning ◽  
Local Optimum ◽  
Inverse Reinforcement Learning ◽  
High Quality ◽  
Overall Performance

The performance of adversarial dialogue generation models relies on the quality of the reward signal produced by the discriminator. The reward signal from a poor discriminator can be very sparse and unstable, which may lead the generator to fall into a local optimum or to produce nonsense replies. To alleviate the first problem, we first extend a recently proposed adversarial dialogue generation method to an adversarial imitation learning solution. Then, in the framework of adversarial inverse reinforcement learning, we propose a new reward model for dialogue generation that can provide a more accurate and precise reward signal for generator training. We evaluate the performance of the resulting model with automatic metrics and human evaluations in two annotation settings. Our experimental results demonstrate that our model can generate more high-quality responses and achieve higher overall performance than the state-of-the-art.

Online Social Exergames for Seniors

2020 ◽  
pp. 1599-1631
Author(s):  
Stathis Th. Konstantinidis ◽  
Ellen Brox ◽  
Per Egil Kummervold ◽  
Josef Hallberg ◽  
Gunn Evertsen ◽  
...  
Keyword(s):  
Quality Of Life ◽  
Physical Activity ◽  
Physical Training ◽  
State Of The Art ◽  
Social Contact ◽  
High Quality ◽  
Current State ◽  
The Future ◽  
The Impact

The population is getting older, and the resources for care will be even more limited in the future than they are now. There is thus an aim for the society that the seniors can manage themselves as long as possible, while at the same time keeping a high quality of life. Physical activity is important to stay fit, and social contact is important for the quality of life. The aim of this chapter is to provide a state-of-the-art of online social exergames for seniors, providing glimpses of senior users' opinions and games limitations. The importance of the motivational techniques is emphasized, as well as the impact that the exergames have to seniors. It contributes to the book objectives focusing on current state and practice in health games for physical training and rehabilitation and the use of gamification, exploring future opportunities and uses of gamification in eHealth and discussing the respective challenges and limitations.

scholarly journals CNN BASED RETINAL IMAGE UPSCALING USING ZERO COMPONENT ANALYSIS

2017 ◽  
Vol XLII-2/W4 ◽  
pp. 27-31 ◽  
Author(s):  
A. Nasonov ◽  
K. Chesnakov ◽  
A. Krylov
Keyword(s):  
Medical Image ◽  
Visual Analysis ◽  
Preparation Method ◽  
State Of The Art ◽  
Medical Image Processing ◽  
Main Idea ◽  
Objective Evaluation ◽  
Component Analysis ◽  
High Quality

The aim of the paper is to obtain high quality of image upscaling for noisy images that are typical in medical image processing. A new training scenario for convolutional neural network based image upscaling method is proposed. Its main idea is a novel dataset preparation method for deep learning. The dataset contains pairs of noisy low-resolution images and corresponding noiseless highresolution images. To achieve better results at edges and textured areas, Zero Component Analysis is applied to these images.<br><br> The upscaling results are compared with other state-of-the-art methods like DCCI, SI-3 and SRCNN on noisy medical ophthalmological images. Objective evaluation of the results confirms high quality of the proposed method. Visual analysis shows that fine details and structures like blood vessels are preserved, noise level is reduced and no artifacts or non-existing details are added. These properties are essential in retinal diagnosis establishment, so the proposed algorithm is recommended to be used in real medical applications.

scholarly journals Dialog State Tracking with Reinforced Data Augmentation

2020 ◽  
Vol 34 (05) ◽  
pp. 9474-9481
Author(s):  
Yichun Yin ◽  
Lifeng Shang ◽  
Xin Jiang ◽  
Xiao Chen ◽  
Qun Liu
Keyword(s):  
Data Augmentation ◽  
State Of The Art ◽  
The State ◽  
Training Data ◽  
Quality Data ◽  
Specific Context ◽  
High Quality ◽  
High Quality Data ◽  
Fine Grained ◽  
State Tracking

Neural dialog state trackers are generally limited due to the lack of quantity and diversity of annotated training data. In this paper, we address this difficulty by proposing a reinforcement learning (RL) based framework for data augmentation that can generate high-quality data to improve the neural state tracker. Specifically, we introduce a novel contextual bandit generator to learn fine-grained augmentation policies that can generate new effective instances by choosing suitable replacements for specific context. Moreover, by alternately learning between the generator and the state tracker, we can keep refining the generative policies to generate more high-quality training data for neural state tracker. Experimental results on the WoZ and MultiWoZ (restaurant) datasets demonstrate that the proposed framework significantly improves the performance over the state-of-the-art models, especially with limited training data.

The Interface Between Marketing and Sales: The State of the Art and a Research Agenda

Marketing ZFP ◽  
2021 ◽  
Vol 43 (1-2) ◽  
pp. 9-22
Author(s):  
Sören A. Radtke ◽  
Marian E. Paul
Keyword(s):  
Empirical Research ◽  
Research Agenda ◽  
Business Performance ◽  
State Of The Art ◽  
The State ◽  
Future Research ◽  
High Quality

Marketing and sales often have to work hand in hand. Therefore, several studies have investigated the drivers and consequences of the quality of cooperation between the two departments. We review empirical research on the effect of the quality of cooperation on business performance and on the drivers of the quality of cooperation, to achieve two objectives. First, we summarise the most important findings on the marketing–sales interface in a compact and structured way to give guidance to managers on how to facilitate high-quality cooperation. Second, we identify the major gaps in the literature and outline a research agenda with suggestions for future research on how to address them.

scholarly journals Unseen Word Representation by Aligning Heterogeneous Lexical Semantic Spaces

2019 ◽  
Vol 33 ◽  
pp. 6900-6907 ◽  
Author(s):  
Victor Prokhorov ◽  
Mohammad Taher Pilehvar ◽  
Dimitri Kartsaklis ◽  
Pietro Lio ◽  
Nigel Collier
Keyword(s):  
Training Data ◽  
Lexical Resources ◽  
Rare Word ◽  
Word Similarity ◽  
Performance Improvements ◽  
Space Transformation ◽  
Word Representation ◽  
Consistent Performance ◽  
Cross Lingual

Word embedding techniques heavily rely on the abundance of training data for individual words. Given the Zipfian distribution of words in natural language texts, a large number of words do not usually appear frequently or at all in the training data. In this paper we put forward a technique that exploits the knowledge encoded in lexical resources, such as WordNet, to induce embeddings for unseen words. Our approach adapts graph embedding and cross-lingual vector space transformation techniques in order to merge lexical knowledge encoded in ontologies with that derived from corpus statistics. We show that the approach can provide consistent performance improvements across multiple evaluation benchmarks: in-vitro, on multiple rare word similarity datasets, and invivo, in two downstream text classification tasks.

scholarly journals PanSVR: Pan-Genome Augmented Short Read Realignment for Sensitive Detection of Structural Variations

2021 ◽  
Vol 12 ◽  
Author(s):  
Gaoyang Li ◽  
Tao Jiang ◽  
Junyi Li ◽  
Yadong Wang
Keyword(s):  
High Throughput Sequencing ◽  
State Of The Art ◽  
Sequencing Data ◽  
Structural Variations ◽  
High Quality ◽  
Structure Variation ◽  
Short Read ◽  
Pan Genome ◽  
Limited Length

The comprehensive discovery of structure variations (SVs) is fundamental to many genomics studies and high-throughput sequencing has become a common approach to this task. However, due the limited length, it is still non-trivial to state-of-the-art tools to accurately align short reads and produce high-quality SV callsets. Pan-genome provides a novel and promising framework to short read-based SV calling since it enables to comprehensively integrate known variants to reduce the incompleteness and bias of single reference to breakthrough the bottlenecks of short read alignments and provide new evidences to the detection of SVs. However, it is still an open problem to develop effective computational approaches to fully take the advantage of pan-genomes. Herein, we propose Pan-genome augmented Structure Variation calling tool with read Re-alignment (PanSVR), a novel pan-genome-based SV calling approach. PanSVR uses several tailored methods to implement precise re-alignment for SV-spanning reads against well-organized pan-genome reference with plenty of known SVs. PanSVR enables to greatly improve the quality of short read alignments and produce clear and homogenous SV signatures which facilitate SV calling. Benchmark results on real sequencing data suggest that PanSVR is able to largely improve the sensitivity of SV calling than that of state-of-the-art SV callers, especially for the SVs from repeat-rich regions and/or novel insertions which are difficult to existing tools.

scholarly journals LLOD-Driven Bilingual Word Embeddings Rivaling Cross-Lingual Transformers in Quality of Life Concept Detection from French Online Health Communities

2021 ◽  
Author(s):  
Katharina Allgaier ◽  
Susana Veríssimo ◽  
Sherry Tan ◽  
Matthias Orlikowski ◽  
Matthias Hartung
Keyword(s):  
Quality Of Life ◽  
Word Embeddings ◽  
Concept Detection ◽  
Lexical Resources ◽  
Online Health Communities ◽  
Related Quality ◽  
Health Communities ◽  
Target Languages ◽  
Cross Lingual

We describe the use of Linguistic Linked Open Data (LLOD) to support a cross-lingual transfer framework for concept detection in online health communities. Our goal is to develop multilingual text analytics as an enabler for analyzing health-related quality of life (HRQoL) from self-reported patient narratives. The framework capitalizes on supervised cross-lingual projection methods, so that labeled training data for a source language are sufficient and are not needed for target languages. Cross-lingual supervision is provided by LLOD lexical resources to learn bilingual word embeddings that are simultaneously tuned to represent an inventory of HRQoL concepts based on the World Health Organization’s quality of life surveys (WHOQOL). We demonstrate that lexicon induction from LLOD resources is a powerful method that yields rich and informative lexical resources for the cross-lingual concept detection task which can outperform existing domain-specific lexica. Furthermore, in a comparative evaluation we find that our models based on bilingual word embeddings exhibit a high degree of complementarity with an approach that integrates machine translation and rule-based extraction algorithms. In a combined configuration, our models rival the performance of state-of-the-art cross-lingual transformers, despite being of considerably lower model complexity.

Sign in / Sign up

Export Citation Format

Share Document