M.Phil / MS

Now showing 1 - 2 of 2

Urdu-English Machine Transliteration using Neural Networks
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2019) Usman Mohy ud Din; FA16-RCS-007; LHR TP 5776; Dr. Muhammad Waqas Anwar
Machine translation has gained much attention in recent years. It is a sub-field of computational linguistic which focus on translating text from one language to other language. Among different translation techniques, neural network currently leading the domain with its capabilities of providing a single large neural network with attention mechanism, sequence-to-sequence and long-short term modelling. Despite significant progress in domain of machine translation, translation of out-of-vocabulary words(OOV) which include technical terms, named-entities, foreign words are still a challenge for current state-of-art translation systems, and this situation becomes even worse while translating between low resource languages or languages having different structures. Due to morphological richness of a language, a word may have different meninges in different context. In such scenarios, translation of word is not only enough in order provide the correct/quality translation. Transliteration is a way to consider the context of word/sentence during translation. For low resource language like Urdu, it is very difficult to have/find parallel corpus for transliteration which is large enough to train the system. In this work, we presented transliteration technique based on Expectation Maximization (EM) which is un-supervised and language independent. Systems learns the pattern and out-of-vocabulary (OOV) words from parallel corpus and there is no need to train it on transliteration corpus explicitly. This approach is tested on three models of statistical machine translation (SMT) which include phrase based, hierarchical phrase-based and factor based models and two models of neural machine translation which include LSTM and transformer model. On SMT models, there is gain of 0.63 to 0.91 in BLEU score while on NMT models, there is gain of 1.28 to 2.05 in BLEU which are better than previous baseline scores. Our approach shows promising results in translation of Urdu text into English which is mostly neglected due to its complexities. We also discussed the results, different challenges faced during this work and effect of right pre-processing techniques
Urdu Word Sense Disambiguation using Siamese Neural Networks
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2020) Waqar Ashiq; SP19-RCS-013; LHR TP 6419; Dr. Rao Muhammad Adeel Nawab
The process of Word Sense Disambiguation (WSD) is to recognize the exact sense of the targeted polysemous terms in the given context. Word sense ambiguities exist in all human languages, and humans can easily solve this ambiguity but it’s a tough task for machines to solve automatically. WSD is a significant long-established task in the area of natural language processing (NLP) with a remarkable contribution in numerous applications. The task of WSD has been categorized into (1) Lexical Sample, and (2) All-Words WSD. In literature, the problem of Urdu WSD has been mainly addressed using feature-based machine learning methods (based on manual feature engineering). A major limitation of manual feature engineering is that it requires a lot of time and endeavors to develop machine learning methods in Urdu WSD. To overcome the limitations of manual feature engineering, deep learning approaches are proposed, and they have produced promising results for various NLP tasks. To fulfill the gap in WSD research, we developed and apply state-of-the-art Siamese Neural Network (SNN) based approaches for both tasks for the Urdu Language. We developed the SNN based approaches for both WSD tasks using six deep learning models (CNN, RNN, LSTM, BiLSTM, GRU, and BiGRU) with the combination of three distance measure functions including Euclidean distance, Manhattan distance, and Cosine similarity. These Siamese network features of all deep learning models are combined for WSD classification using eight machine learning classifiers with two well-known feature selection methods (RFECV and Chi-Square). Additionally, for the All-words task SNN features are combined with n-gram (unigram and bigram) features. The developed SNN based approaches are evaluated on well-known benchmark corpora which include (1) UAW-WSD-18 Corpus for All-words WSD and (2) ULS WSD-18-Corpus for Lexical sample WSD task. After extensive experimentation, the proposed approach produced state-of-the-art results (Accuracy = 64%) in All-words WSD and outperform the baseline results (Accuracy = 57.71%). The results of Lexical sample WSD are not improved because of very few instances of each ambiguous word in corpora for deep learning approaches.

M.Phil / MS

Browse

Filters

Settings

Sort By

Results per page

Search Results