Multi-task Learning in Translating English Language into Arabic Language

Kareema G. Milad, Yasser F. Hassan, Ashraf S. El Sayed

Abstract


Machine learning techniques usually require a large number of training samples to achieve maximum benefit. In this case, limited training samples are not enough to learn models; recently there has been a growing interest in machine learning methods that can exploit knowledge from such other tasks to improve performance. Multi-task learning was proposed to solve this problem. Multi-task learning is a machine learning paradigm for learning a number tasks simultaneously, exploiting commonalities between them. When there are relations between the tasks to learn, it can be advantageous to learn all these tasks simultaneously instead of learning each task independently. In this paper, we propose translate language from source language to target language using Multi-task learning, for our need building a relation extraction system between the words in the texts, we applied related tasks ( part-of-speech , chunking and named entity recognition) and train it's in parallel on annotated data using hidden markov model, Experiments of text translation task show that our proposed work can improve the performance of a translation task with the help of other related tasks.

Full Text:

PDF

References


Zhou, Jiayu. Multi-Task Learning and Its Applications to Biomedical Informatics.Diss. Arizona State University, (2014).‏

Luong, Minh-Thang, et al. "Multi-task sequence to sequence learning." arXiv preprint arXiv: (2015).‏

Li, Changsheng, et al. "A Self-Paced Regularization Framework for Multilabel Learning." IEEE Transactions onNeural Networks and Learning Systems (2017).

Ruder, Sebastian. "An overview of multi-task learning in deep neural networks." arXiv preprint arXiv: (2017).‏

Zhang, Yu, et al. "A Survey on Multi-Task Learning." arXiv preprint arXiv: (2017).‏

Bonadiman, et al. "Multitask Learning with Deep Neural Networks for Community Question Answering." arXiv preprint arXiv: (2017).‏

Collobert, , et al. "Natural language processing (almost) from scratch." Journal of Machine Learning Research 2493-2537(2011).

Badr, Ibrahim, , et al. "Syntactic phrase reordering for English-to-Arabic statistical machine translation." Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics. Association for Computational Linguistics,(2009).‏

Jurafsky, , et al.. "Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition."‏ (2017).

Jain, Ubeeka, et al. "Text Chunker for Punjabi." Indian Journal of Science and Technology, Vol 8(35) (2015).‏

Malik, et al. "Urdu Named Entity Recognition System using Hidden Markov Model." Pakistan Journal of Engineering and Applied Sciences (2017).‏

Morwal, et al. "Named entity recognition using hidden markov model (hmm): An experimental result on Hindi, Urdu and Marathi languages." Int. J. Adv. Res. Comput. Sci. Softw. Eng 3.4 (2013).‏

Awasthi, et al. "Part of speech tagging and chunking with hmm and crf." Proceedings of NLP Association of India (NLPAI) Machine Learning Contest (2006).‏

Fu, et al. "Chinese text chunking using lexicalized HMMs." Machine Learning and Cybernetics, . Proceedings of International Conference on. IEEE, (2005).

Paul, et al. "Hidden Markov model based part of speech tagging for Nepali language." Advanced Computing and Communication (ISACC), International Symposium on. IEEE, (2015).‏

Okhovvat, et al. "A hidden Markov model for Persian part-of-speech tagging." Procedia Computer Science : 977-981(2011).

Liu, et al. "Representation Learning Using Multi-Task Deep Neural Networks for Semantic Classification and Information Retrieval." HLT-NAACL. (2015).‏

Tan et al.. "Prediction of anti-cancer drug response by kernelized multi-task learning." Artificial intelligence in medicine : 70-77(2016).‏

Ronan, et al. "A unified architecture for natural language processing: Deep neural networks with multitask learning." Proceedings of the 25th international conference on Machine learning. ACM, (2008).‏

Liu, et al.. "Recurrent neural network for text classification with multi-task learning." arXiv preprint arXiv:1605.05101 (2016).‏

Hatem, et al. "Syntactic reordering for Arabic-English phrase-based machine translation." Database Theory and Application, Bio-Science and Bio-Technology. Springer, Berlin, Heidelberg.198-206(2010).‏

Prasomsuk, et al. "Thai to Khmer Rule-Based Machine Translation Using Reordering Word to Phrase." International Journal of Computer Theory and Engineering (2017).‏

https://github.com/FranckDernoncourt/NeuroNER/blob/master/data/conll2003/en/train.txt.




DOI: https://doi.org/10.23956/ijermt.v7i5.35

Refbacks

  • There are currently no refbacks.