-
Spanish-Turkish Low-Resource Machine Translation: Unsupervised Learning vs Round-Tripping
Tianyi Xu,
Ozge Ilkim Ozbek,
Shannon Marks,
Sri Korrapati,
Benyamin Ahmadnia
Issue:
Volume 4, Issue 2, December 2020
Pages:
42-49
Received:
28 May 2020
Accepted:
18 June 2020
Published:
23 July 2020
Abstract: The quality of data-driven Machine Translation (MT) strongly depends on the quantity as well as the quality of the training dataset. However, collecting a large set of training parallel texts is not easy in practice. Although various approaches have already been proposed to overcome this issue, the lack of large parallel corpora still poses a major practical problem for many language pairs. Since monolingual data plays an important role in boosting fluency for Neural MT (NMT) models, this paper investigates and compares the performance of two learning-based translation approaches for Spanish-Turkish translation as a low-resource setting in case we only have access to large sets of monolingual data in each language; 1) Unsupervised Learning approach, and 2) Round-Tripping approach. Either approach completely removes the need for bilingual data or enables us to train the NMT system relying on monolingual data only. We utilize an Attention-based NMT (Attentional NMT) model, which leverages a careful initialization of the parameters, the denoising effect of language models, and the automatic generation of bilingual data. Our experimental results demonstrate that the Unsupervised Learning approach outperforms the Round-Tripping approach in Spanish-Turkish translation and vice versa. These results confirm that the Unsupervised Learning approach is still a reliable learning-based translation technique for Spanish-Turkish low-resource NMT.
Abstract: The quality of data-driven Machine Translation (MT) strongly depends on the quantity as well as the quality of the training dataset. However, collecting a large set of training parallel texts is not easy in practice. Although various approaches have already been proposed to overcome this issue, the lack of large parallel corpora still poses a major...
Show More
-
The Taxonomy of Living Organisms Using Self-organizing Map
Issue:
Volume 4, Issue 2, December 2020
Pages:
50-61
Received:
30 May 2020
Accepted:
15 June 2020
Published:
7 September 2020
Abstract: The Self Organizing Map (SOM) is an unsupervised network algorithm that projects high dimensional data into low dimensional maps. The projection preserves the topology of the data so that similar data items are mapped to nearby locations on the map. The algorithm has been so popular because of its application in Computer Science and other areas; it has been applied in speech recognition, pattern identification, control engineering, earthquake detection et al. This research aimed to apply the SOM in the taxonomy of living organisms using 46 attributes. 68 animals from 6 phyla were considered and 46 attributes were used detailing their physical features, physiological features, evolution, adaptation, habitat et al. The features extracted were converted to 0s and 1s for the SOM algorithm to process. The result shows 96.569% accuracy of the SOM’s classification but better accuracy can be obtained if the SOM had processed the data for about 1000 iterations. This research revealed that SOM is a veritable tool or algorithm that can be used to classify living organisms. This research will help taxonomists, biologists and students who spend much time in classifying living organism and it will be of help to researchers who want to explore the SOM algorithm as a solution to taxonomy of living organisms. The SOM will ease taxonomy and will help to minimize the stress and time involved in classifying thousands of living organisms.
Abstract: The Self Organizing Map (SOM) is an unsupervised network algorithm that projects high dimensional data into low dimensional maps. The projection preserves the topology of the data so that similar data items are mapped to nearby locations on the map. The algorithm has been so popular because of its application in Computer Science and other areas; it...
Show More
-
A Neural Network Scheme for Monetary Policy Rate Validation in Nigeria
Oloruntoba Samuel Ogundele,
Augustine Ujunwa,
Aminu Ado Mohammed
Issue:
Volume 4, Issue 2, December 2020
Pages:
62-72
Received:
4 October 2020
Accepted:
12 November 2020
Published:
11 December 2020
Abstract: This research work is an exploratory study that tried to examine the viability of adopting artificial neural network (ANN), an aspect of machine learning in the analysis of monetary data for the design and validation of monetary policy from both optimistic and normative approach. Methodologically, the research is motivated by the work of [33] which used the Greenbook real time data of the U.S. Federal Reserve's in the analysis of monetary policy reaction functions in forecasting performance using ANN. Following the work on the adoption of this technique, we tried to develop a framework based on machine learning for policy rate forecasting by analysing macroeconomic data with the aim of guiding and aiding monetary authority in making monetary policy decisions. From the results, the ANN perform better in predicting the monetary policy rate compared to the linear models and the univariate process. It also revealed the non-linearity in the behavior of the monetary policy rate in Nigeria during the study period. While the work does not mean to advocate that machine will replace human-being in policy rate determination in the monetary policy-making process; we believe that the development and implementation of this system would support building effective prediction system which can be validated. The result from the designed system is expected to enhance credibility, confidence and transparency of central banks in making an independent decision (s) based on objective forecasts and implied analysis in setting policy through a well-structured comparison of results.
Abstract: This research work is an exploratory study that tried to examine the viability of adopting artificial neural network (ANN), an aspect of machine learning in the analysis of monetary data for the design and validation of monetary policy from both optimistic and normative approach. Methodologically, the research is motivated by the work of [33] which...
Show More
