Search

Machine translation (MT) is an emerging research as well as application area in the contemporary world. It is receiving significant attention from academia, industry and corporate houses. A wide range of translation techniques are being applied either individually or in combination for machine translation of different languages across the globe. However, there are still many languages that are either completely missing or poorly visible on the machine translation map. The Kashmiri language is one such language where very little or negligible work has been done related to its machine translation. This paper aims to present a Kashmiri-to-English Machine Translation System and highlight various features of the Kashmiri language. The system is based on machine intelligence having the ability to learn various translation rules from the translated set of input sentences, using Long Short-term Memory (LSTM) architecture for deep sequence learning. The paper also discusses various challenges related to machine translation from Kashmiri to English or other languages. The work presented in this paper is the first of its nature and can serve as a bedrock for research community interested to work on machine translation of Kashmiri language. [ABSTRACT FROM AUTHOR]

Recently, Python is the most-widely used language in artificial intelligence (AI) projects requiring huge amount of CPU and memory resources, and long execution time for training. For saving the project duration and making AI software systems more reliable, it is inevitable to handle exceptions appropriately at the code level. However, handling exceptions highly relies on developer's experience. This is because, as an interpreter-based programming language, it does not force a developer to catch exceptions during development. In order to resolve this issue, we propose an approach to suggesting appropriate exceptions for the AI code segments during development after training exceptions from the existing handling statements in the AI projects. This approach learns the appropriate token units for the exception code and pretrains the embedding model to capture the semantic features of the code. Additionally, the attention mechanism learns to catch the salient features of the exception code. For evaluating our approach, we collected 32,771 AI projects using two popular AI frameworks (i.e. Pytorch and Tensorflow) and we obtained the 0.94 of Area under the Precision-Recall Curve (AUPRC) on average. Experimental results show that the proposed method can support the developer's exception handling with better exception proposal performance than the compared models. [ABSTRACT FROM AUTHOR]