PHD Research proposal in Deep Learning for Natural Language Processing (NLP)

With the progressive evolution of the Internet and social media, there is a rapid rise in online data. As the volume of data grows, there is a necessity to handle and extract relevant information from the massive knowledge base is getting more difficult, such challenges and difficulties overcome by using Natural language processing (NLP) techniques [1]. Recently, the advent of deep learning techniques essentially alters the landscapes in the areas include robotics, artificial intelligence, along with speech, vision, game playing, natural language and so on. Notably, the striking achievement of deep learning in an extensive range of natural language processing (NLP) applications has functioned as a benchmark for the advancement in the significant task of artificial intelligence [2]. It attempts to characterize and understand the text based on the arbitrary notions of content, morphemes, clauses, and other components of the linguistic structure to reveal the encoded content in the human language. As the capability of representational learning of complex task, the deep learning models outperforms in natural language processing for the opinion mining, whereas the sentiment among reviews and post are identified to estimate the customer opinion [3].

Furthermore, it widely applied in automatic summarization, question answering system, text classification, language modeling, information retrieval, spam filter, machine translation, speech recognition, and so on [4].

In practice, there is a massive amount of knowledge sources for the NLP like linguistic knowledge (e.g., Lexicon, grammar), world knowledge (e.g., Wikipedia), and symbols. The deep learning model in the NLP tasks has not yet made any significant progress in the efficient utilization of knowledge. Also, symbol representation using the deep learning methods eases the interpretation and the manipulation. At the same time, the vector representations are more robust to Noisy and Ambiguous data [5]. However, by taking advantages of both the symbol data and vector representation data is still a bottleneck for natural language processing. The deep learning requires an external force when confronting the complex task of natural language processing.

The deep learning methods are significantly out-compete the other methods on several challenging natural language constraints based on the simple and singular models. Despite it lacks in interpretation, theoretical foundation, and entails a potent computing resource and a massive amount of training data. It demands substantial training data to learn the regularity of the specific domain. Furthermore, it is more vulnerable to overfit the data when the availability of training data becomes smaller. It often suffers the issues owing to the lack of inference. Also, the deep learning model based on natural language processing meets several challenges when dealing with the context-sensitive nature of the text.

Reference:

  • [1] Nadkarni, Prakash M., Lucila Ohno-Machado, and Wendy W. Chapman, “Natural language processing: an introduction”, Journal of the American Medical Informatics Association, Vol.18, No.5, pp.544-551, 2011.

  • [2] Meurers, Detmar, “Natural language processing and language learning”, The Encyclopedia of Applied Linguistics, 2012.

  • [[3] Otter, Daniel W., Julian R. Medina, and Jugal K. Kalita, “A survey of the usages of deep learning in natural language processing”, arXiv preprint arXiv:1807.10854, 2018.

  • [4] Young, Tom, Devamanyu Hazarika, Soujanya Poria, and Erik Cambria, “Recent trends in deep learning based natural language processing”, IEEE Computational intelligence magazine, Vol.13, No.3, pp.55-75, 2018.

  • [5] Marcus, Gary, “Deep learning: A critical appraisal”, arXiv preprint arXiv:1801.00631, 2018.

Leave Comment

Your email address will not be published. Required fields are marked *

clear formSubmit