Showing papers by "Zuhair Bandar published in 2013"

User's utterance classification using machine learning for Arabic Conversational Agents

Abstract: This paper presents a novel technique for the classification of Arabic sentences as Dialogue Acts, based on structural information contained in Arabic function words. It focuses on classifying questions and non-questions utterances as they are used in Conversational Agents. The proposed technique extracts function words features by replacing them with numeric tokens and replacing each content word with a standard numeric token. The Decision Tree has been chosen for this work to extract the classification rules. Experiments provide evidence for highly effective classification. The extracted classification rules will be embedded into a Conversational Agent called ArabChat in order to classify Arabic utterances before further processing on these utterances. This paper presents a complement work for the ArabChat to improve its performance by differentiating among question-based and non question-based utterances.

AWSS: An Algorithm for Measuring Arabic Word Semantic Similarity

Abstract: Semantic similarity is an essential component of numerous applications in fields such as natural language processing, artificial intelligence, linguistics, and psychology. Most of the reported work has been done in English. To the best of our knowledge, there is no word similarity measure developed specifically for Arabic. This paper presents a method to measure the semantic similarity between two Arabic words in the Arabic knowledge base. The semantic similarity is calculated through the combination of the common and different attributes between the Arabic words in the hierarchy semantic net. We use a previously developed Arabic word benchmark dataset to optimize and evaluate the Arabic measure. Experimental evaluation indicates that the Arabic measure is performing well. It has achieved a correlation value of 0.894 compared with the average value of human participants of 0.893 on evaluation dataset.

FAST: A fuzzy semantic sentence similarity measure

Abstract: A problem in the field of semantic sentence similarity is the inability of sentence similarity measures to accurately represent perception based (fuzzy) words that are commonly used in natural language. This paper presents a new sentence similarity measure that attempts to solve this problem. The new measure, Fuzzy Algorithm for Similarity Testing (FAST) is an ontology based similarity measure that uses concepts of fuzzy and computing with words to allow for the accurate representation of fuzzy based words. Through human experimentation fuzzy sets were created for six categories of words based on their levels of association with particular concepts. These fuzzy sets were then defuzzified and the results used to create new ontological relations between the words. Using these relationships allows for the creation of a new ontology based semantic text similarity algorithm that is able to show the effect of fuzzy words on computing sentence similarity as well as the effect that fuzzy words have on non-fuzzy words within a sentence. Experiments on FAST were conducted using a new fuzzy dataset, the creation of which is described in this paper. The results of the evaluation showed that there was an improved level of correlation between FAST and human test results over two existing sentence similarity measures.

Optimizing Features for Dialogue Act Classification

Abstract: Natural language dialogue is an important component of interaction between ordinary users and complex computer applications. Short Text Semantic Similarity algorithms have been developed to improve the efficiency of producing sophisticated dialogue systems. Such algorithms are currently unable to discriminate between different dialogue acts (assertions, questions, instructions etc.), requiring the addition of efficient dialogue act classifiers to enhance them. The Slim Function Word Classifier (SFWC) has proved promising, particularly in its computational simplicity. This study optimizes the SFWC by clustering function word features using grammatical principles. Experiments show a significant improvement in classification accuracy for a selection of sentence forms which were challenging for the unoptimized SFWC. Results are expected to be applicable to many intelligent text processing applications ranging from question answering to meeting summarization.

FATHOMing out interdisciplinary research transfer

Abstract: This paper presents a case study on the development and deployment of a computerised, non-invasive psychological profiling system which detects human comprehension through the monitoring of multiple channels of facial nonverbal behaviour using Artificial Neural Networks (ANN). Prior work on an earlier system known as Silent Talker, led to collaborations and a funded project with Family Health International 360 (FHI 360) in collaboration with the National Institute of Medical Research (NIMR), to produce the FATHOM system for measuring comprehension of the informed consent process amongst women in Tanzania. This paper describes the process of taking a working research prototype and deploying the system in a real working environment. The paper discusses the process of contract negotiation, global ethics and intellectual property rights. The FATHOM system and initial results are described.