Skip to main content

Research Repository

Advanced Search

All Outputs (11)

CAM: A Combined Attention Model for Natural Language Inference (2018)
Presentation / Conference Contribution
Gajbhiye, A., Jaf, S., Al-Moubayed, N., Bradley, S., & McGough, A. S. (2018). CAM: A Combined Attention Model for Natural Language Inference. In N. Abe, H. Liu, C. Pu, X. Hu, N. Ahmed, M. Qiao, …J. Saltz (Eds.), 2018 IEEE International Conference on Big Data (Big Data) ; proceedings (1009-1014). https://doi.org/10.1109/bigdata.2018.8622057

Natural Language Inference (NLI) is a fundamental step towards natural language understanding. The task aims to detect whether a premise entails or contradicts a given hypothesis. NLI contributes to a wide range of natural language understanding appl... Read More about CAM: A Combined Attention Model for Natural Language Inference.

An Exploration of Dropout with RNNs for Natural Language Inference (2018)
Presentation / Conference Contribution
Gajbhiye, A., Jaf, S., Al-Moubayed, N., McGough, A. S., & Bradley, S. (2018, December). An Exploration of Dropout with RNNs for Natural Language Inference. Presented at ICANN 2018: 27th International Conference on Artificial Neural Networks, Rhodes

Dropout is a crucial regularization technique for the Recurrent Neural Network (RNN) models of Natural Language Inference (NLI). However, dropout has not been evaluated for the effectiveness at different layers and dropout rates in NLI models. In thi... Read More about An Exploration of Dropout with RNNs for Natural Language Inference.

Improved Arabic Characters Recognition by Combining Multiple Machine Learning Classifiers (2017)
Presentation / Conference Contribution
Alabbas, M., Khudeyer, R., Jaf, S., Dong, M., Tseng, Y., Lu, Y., …Li, H. (2017). Improved Arabic Characters Recognition by Combining Multiple Machine Learning Classifiers. In Proceedings of the 2016 International Conference on Asian Language Processing (IALP), 21-23 November 2016, Tainan, Taiwan (262-265). https://doi.org/10.1109/ialp.2016.7875982

In this paper, we investigate a range of strategies for combining multiple machine learning techniques for recognizing Arabic characters, where we are faced with imperfect and dimensionally variable input characters. Experimental results show that co... Read More about Improved Arabic Characters Recognition by Combining Multiple Machine Learning Classifiers.

A Semi-automatic Approach to Identifying and Unifying Ambiguously Encoded Arabic-Based Characters (2017)
Presentation / Conference Contribution
Jaf, S., Dong, M., Tseng, Y., Lu, Y., Yu, L., Lee, L., …Li, H. (2017). A Semi-automatic Approach to Identifying and Unifying Ambiguously Encoded Arabic-Based Characters. In Proceedings of the 2016 International Conference on Asian Language Processing (IALP), 21-23 November 2016, Tainan, Taiwan (228-231). https://doi.org/10.1109/ialp.2016.7875974

In this study, we outline a potential problem in normalising texts that are based on a modified version of the Arabic alphabet. One of the main resources available for processing resource-scarce languages is raw text collected from the Internet. Many... Read More about A Semi-automatic Approach to Identifying and Unifying Ambiguously Encoded Arabic-Based Characters.

Optimize BpNN using new breeder genetic algorithm (2016)
Presentation / Conference Contribution
Alabass, M., Jaf, S., Abdullah, A. M., Hassanien, A. E., Shaalan, K., Gaber, T., …Tolba, M. F. (2017). Optimize BpNN using new breeder genetic algorithm. In Proceedings of the International Conference on Advanced Intelligent Systems and Informatics 2016 (373-382). https://doi.org/10.1007/978-3-319-48308-5_36

In this paper, the ability of genetic algorithms in designing artificial neural network (ANN) is investigated. The multi-layer network (MLN) is taken into account as the ANN structure to be optimized. The idea presented here is to use the genetic alg... Read More about Optimize BpNN using new breeder genetic algorithm.

A Simple Approach to Unify Ambiguously Encoded Kurdish Characters (2016)
Presentation / Conference Contribution
Jaf, S. (2016). A Simple Approach to Unify Ambiguously Encoded Kurdish Characters.

In this study we outline a potential problem in the normalisation stage of processing texts that are based on a modified version of the Arabic alphabet. The main source of resources available for processing resource-scarce languages is raw text. We h... Read More about A Simple Approach to Unify Ambiguously Encoded Kurdish Characters.

The Selection of Classifiers for a Data-driven Parser (2015)
Presentation / Conference Contribution
Jaf, S., Ramsay, A., Sharp, B., Lubaszewski, W., & Delmonte, R. (2015). The Selection of Classifiers for a Data-driven Parser. In Natural language processing and cognitive science : proceedings 2015 (39-49)

There is a large number of classifiers that can be used for generating a parse model; i.e., as an oracle for guiding data-driven parsers when parsing natural languages. In this paper we present a general and simple approach for generating a parse mod... Read More about The Selection of Classifiers for a Data-driven Parser.

Deterministic Choices in a Data-driven Parser (2015)
Presentation / Conference Contribution
Jaf, S., Ramsay, A., Sharp, B., Lubaszewski, W., & Delmonte, R. (2015). Deterministic Choices in a Data-driven Parser. In Natural language processing and cognitive science : proceedings 2015 (95-103)

Data-driven parsers rely on recommendations from parse models, which are generated from a set of training data using a machine learning classifier, to perform parse operations. However, in some cases a parse model cannot recommend a parse action to a... Read More about Deterministic Choices in a Data-driven Parser.

The Application of Constraint Rules to Data-driven Parsing (2015)
Presentation / Conference Contribution
Jaf, S., Ramsay, A., Angelova, G., Bontcheva, K., & Mitkov, R. (2015). The Application of Constraint Rules to Data-driven Parsing. In Recent advances in natural language processing : 10th International conference, RANLP 2015, 7-9 September 2015, Hissar, Bulgaria ; proceedings (232-238)

In this paper, we show an approach to extracting different types of constraint rules from a dependency treebank. Also, we show an approach to integrating these constraint rules into a dependency data-driven parser, where these constraint rules inform... Read More about The Application of Constraint Rules to Data-driven Parsing.

Towards the Development of a Hybrid Parser for Natural Languages (2013)
Presentation / Conference Contribution
Jaf, S., Allan, R., Jones, A. V., & Ng, N. (2013). Towards the Development of a Hybrid Parser for Natural Languages. In 2013 Imperial College Computing Student Workshop (ICCSW’13) (49-56). https://doi.org/10.4230/oasics.iccsw.2013.49

In order to understand natural languages, we have to be able to determine the relations between words, in other words we have to be able to 'parse' the input text. This is a difficult task, especially for Arabic, which has a number of properties that... Read More about Towards the Development of a Hybrid Parser for Natural Languages.