Translation Methods for Animal Images in Li Sao (离骚)

Natural Language Processing for under-resourced languages is now a mainstream research area. However, there are limited studies on Natural Language Processing applications for many indigenous East African languages. As a contribution to covering the current gap of knowledge, this paper focuses on evaluating the application of well-established machine translation methods for one heavily under-resourced indigenous East African language called Lumasaaba. Specifically, we review the most common machine translation methods in the context of Lumasaaba including both rule-based and data-driven methods. Then we apply a state of the art data-driven machine translation method to learn models for automating translation between Lumasaaba and English using a very limited data set of parallel sentences. Automatic evaluation results show that a transformer-based Neural Machine Translation model architecture leads to consistently better BLEU scores than the recurrent neural network-based models. Moreover, the automatically generated translations can be comprehended to a reasonable extent and are usually associated with the source language input.

Download Full-text

Multi-Resolution Autoregressive Graph-to-Graph Translation for Molecules

10.26434/chemrxiv.8266745.v1 ◽

2019 ◽

Author(s):

Wengong Jin ◽

Regina Barzilay ◽

Tommi S Jaakkola

Keyword(s):

Drug Discovery ◽

State Of The Art ◽

Molecular Graph ◽

Biochemical Properties ◽

Large Margin ◽

Previous State ◽

Translation Methods ◽

Atom Level ◽

Precursor Molecules ◽

Prior State

The problem of accelerating drug discovery relies heavily on automatic tools to optimize precursor molecules to afford them with better biochemical properties. Our work in this paper substantially extends prior state-of-the-art on graph-to-graph translation methods for molecular optimization. In particular, we realize coherent multi-resolution representations by interweaving trees over substructures with the atom-level encoding of the original molecular graph. Moreover, our graph decoder is fully autoregressive, and interleaves each step of adding a new substructure with the process of resolving its connectivity to the emerging molecule. We evaluate our model on multiple molecular optimization tasks and show that our model outperforms previous state-of-the-art baselines by a large margin.

Download Full-text

Using Convolutional Neural Networks to measure the contribution of visual features to the representation of object animacy in the brain

10.31237/osf.io/fxz4q ◽

2019 ◽

Cited By ~ 1

Author(s):

Sushrut Thorat

Keyword(s):

Neural Networks ◽

Convolutional Neural Networks ◽

Temporal Cortex ◽

Large Degree ◽

Visual Features ◽

Visual Feature ◽

Visual Stream ◽

Feature Information ◽

Ventral Visual Stream ◽

Animal Images

A mediolateral gradation in neural responses for images spanning animals to artificial objects is observed in the ventral temporal cortex (VTC). Which information streams drive this organisation is an ongoing debate. Recently, in Proklova et al. (2016), the visual shape and category (“animacy”) dimensions in a set of stimuli were dissociated using a behavioural measure of visual feature information. fMRI responses revealed a neural cluster (extra-visual animacy cluster - xVAC) which encoded category information unexplained by visual feature information, suggesting extra-visual contributions to the organisation in the ventral visual stream. We reassess these findings using Convolutional Neural Networks (CNNs) as models for the ventral visual stream. The visual features developed in the CNN layers can categorise the shape-matched stimuli from Proklova et al. (2016) in contrast to the behavioural measures used in the study. The category organisations in xVAC and VTC are explained to a large degree by the CNN visual feature differences, casting doubt over the suggestion that visual feature differences cannot account for the animacy organisation. To inform the debate further, we designed a set of stimuli with animal images to dissociate the animacy organisation driven by the CNN visual features from the degree of familiarity and agency (thoughtfulness and feelings). Preliminary results from a new fMRI experiment designed to understand the contribution of these non-visual features are presented.

Download Full-text

A GAN-based temporally stable shading model for fast animation of photorealistic hair

Computational Visual Media ◽

10.1007/s41095-020-0201-9 ◽

2021 ◽

Author(s):

Zhi Qiao ◽

Takashi Kanai

Keyword(s):

Main Idea ◽

Temporal Coherence ◽

Image Translation ◽

Translation Methods

AbstractWe introduce an unsupervised GAN-based model for shading photorealistic hair animations. Our model is much faster than previous rendering algorithms and produces fewer artifacts than other neural image translation methods. The main idea is to extend the Cycle-GAN structure to avoid semitransparent hair appearance and to exactly reproduce the interaction of the lights with the scene. We use two constraints to ensure temporal coherence and highlight stability. Our approach outperforms and is computationally more efficient than previous methods.

Download Full-text

Translation and cultural adaptation of the Pregnancy Physical Activity Questionnaire into Danish using the dual-panel approach: comparison with outcomes from an alternative translation approach

BMC Research Notes ◽

10.1186/s13104-021-05640-6 ◽

2021 ◽

Vol 14 (1) ◽

Author(s):

Jannie Tygesen Schmidt ◽

Josephine Nielsen ◽

Allan Riis ◽

Birgit Tine Larsen

Keyword(s):

Physical Activity ◽

Pregnant Women ◽

Activity Levels ◽

Physical Activity Questionnaire ◽

Culturally Adapted ◽

The Us ◽

Physical Activity Recommendations ◽

Approach Method ◽

Translation Methods ◽

Activity Questionnaire

Abstract Objective Physical activity reduces the risk of pregnancy-related complications. However, pregnant women often reduce their physical activity levels and do not follow the WHO’s physical activity recommendations during pregnancy. To support pregnant women in monitoring physical activity, the self-administered Pregnancy Physical Activity Questionnaire was developed in the US. We translated and cross-cultural adapted the questionnaire using the dual approach method. Meanwhile, and without knowing this, another Danish group simultaneously translated the questionnaire using the method described by Beaton et al. The aim is to present our data and discuss the unplanned purpose of comparing the results from using two different translation methods. Results We translated and cross-culturally adapted the Pregnancy Physical Activity Questionnaire to Danish with the following findings. Two additional items for cycling were included. Three items about spending time on a computer, reading, writing or talking on the phone were not feasible in terms of differentiating between them and these were merged into one item. The item ‘Taking care of an older adult’ was found to be irrelevant in a Danish setting and was removed. Adaptions were similar comparing the two methods. Consequently, using the dual-panel and the methods suggested by Beaton et al. yield similar results when translating and cultural adapting the PPAQ.

Download Full-text

Hybrid Mamdani Fuzzy Rules and Convolutional Neural Networks for Analysis and Identification of Animal Images

Computation ◽

10.3390/computation9030035 ◽

2021 ◽

Vol 9 (3) ◽

pp. 35

Author(s):

Hind R. Mohammed ◽

Zahir M. Hussain

Keyword(s):

Neural Networks ◽

Convolutional Neural Networks ◽

High Speed ◽

Moving Objects ◽

Real Life ◽

Fuzzy Rules ◽

High Rate ◽

Moving Images ◽

Animal Images

Accurate, fast, and automatic detection and classification of animal images is challenging, but it is much needed for many real-life applications. This paper presents a hybrid model of Mamdani Type-2 fuzzy rules and convolutional neural networks (CNNs) applied to identify and distinguish various animals using different datasets consisting of about 27,307 images. The proposed system utilizes fuzzy rules to detect the image and then apply the CNN model for the object’s predicate category. The CNN model was trained and tested based on more than 21,846 pictures of animals. The experiments’ results of the proposed method offered high speed and efficiency, which could be a prominent aspect in designing image-processing systems based on Type 2 fuzzy rules characterization for identifying fixed and moving images. The proposed fuzzy method obtained an accuracy rate for identifying and recognizing moving objects of 98% and a mean square error of 0.1183464 less than other studies. It also achieved a very high rate of correctly predicting malicious objects equal to recall = 0.98121 and a precision rate of 1. The test’s accuracy was evaluated using the F1 Score, which obtained a high percentage of 0.99052.

Download Full-text