• Digital Humanities and Cultural Heritage
• Publications close
• Conference object close
• PS close

Text data, including short texts, constitute a major share of web content. The availability of this data to billions of users triggers frequent plagiarism attacks. Authorship Attribution (AA) seeks to identify the most probable author of a given text based on similarity to the writing style of potential authors. In this paper, we approach AA as a writing style profile generation process, where we group text instances for each author into a single profile. We use Twitter as the source for our short Modern Standard Arabic (MSA) texts. Numerous experiments with various training approaches, tools and features allowed us to settle on a text representation method that relies on text concatenation of Arabic tweets to form chunks, which are then duplicated to reach a precalculated length. These chunks are used to train machine learning models for our 45 author profiles. This allowed us to achieve accuracies up to 99%, which compares favorably with the best results reported in the literature.

Extracting synonyms from dictionaries or corpora is gaining a special attention as synonyms play an important role in improving NLP application performance. This paper presents a survey of the different approaches and trends used in automatically extracting the synonyms. These approaches can be divided into four main categories. The first approach is to find the Synonyms using a translation graph, The second approach is to discover new transition pairs such as (Arabic – English) (English – France) then (Arabic- France). The third approach is to construct new WordNets by exploring synonymy graphs, and the fourth approach is to find similar words from corpora using Deelp Learning methods, such as word embeddings and recently BERT models. The papers also presents comparative analysis between these approoaches, and highlights potential adaptation to generate synonyms automatically in the Arabic language as future work.

Functional and non-functional requirements are equally important in software engineering. Both of them are mixed together within the same software requirement document. Usually, they are expressed in natural languages. So, a lot of human effort is required to classify them. Software requirements classification is a challenging task. Requirements classification can help developers to deliver quality software that meets users' expectations completely. In this paper, we present a Semi-Automated classification approach of Arabic functional and non-functional requirements using a natural language processing (NLP) tool. We propose a set of heuristics based on basic constructs of Arabic sentences in order to extract information from Arabic software requirements to classify the requirements into functional and non-functional requirements. This research aims to help software engineers by reducing the cost and time required in performing manual classification of software requirements.

The extraction of named entities from unstructured text is a crucial component in numerous Natural Language Processing (NLP) applications such as information retrieval, question answering, machine translation, to name but a few. Named-entity Recognition (NER) aims at locating proper nouns from unstructured text and classifying them into a predefined set of types, such as persons, locations, and organizations. There has been extensive research on improving the accuracy of NER in English text. For other languages such as Arabic, extracting Named-entities is quite challenging due to its morphological structure. In this paper, we introduce ArabiaNer, a system employing Conditional Random Field (CRF) learning algorithm with extensive feature engineering steps to effectively extract Arabic named Entities. ArabiaNer produced state-of-the-art results with f1-score of 91.31% when applied on the ANERcrop dataset.

Using pre-trained transformer models such as BERT has proven to be effective in many NLP tasks. This paper presents our work to fine-tune BERT models for Arabic Word Sense Disambiguation (WSD). We treated the WSD task as a sentence-pair binary classification task. First, we constructed a dataset of labeled Arabic context-gloss pairs (~167k pairs) we extracted from the Arabic Ontology and the large lexicographic database available at Birzeit University. Each pair was labeled as True or False and target words in each context were identified and annotated. Second, we used this dataset for fine-tuning three pre-trained Arabic BERT models. Third, we experimented the use of different supervised signals used to emphasize target words in context. Our experiments achieved promising results (accuracy of 84%) although we used a large set of senses in the experiment.

This paper presents a set of experiments to evaluate and compare between the performance of using CBOW Word2Vec and Lemma2Vec models for Arabic Word-in-Context (WiC) disambiguation without using sense inventories or sense embeddings. As part of the SemEval-2021 Shared Task 2 on WiC disambiguation, we used the dev.ar-ar dataset (2k sentence pairs) to decide whether two words in a given sentence pair carry the same meaning. We used two Word2Vec models: Wiki-CBOW, a pre-trained model on Arabic Wikipedia, and another model we trained on large Arabic corpora of about 3 billion tokens. Two Lemma2Vec models was also constructed based on the two Word2Vec models. Each of the four models was then used in the WiC disambiguation task, and then evaluated on the SemEval-2021 test.ar-ar dataset. At the end, we reported the performance of different models and compared between using lemma-based and word-based models. Comment: Accepted at SemEval 2021 Task 2, 8 Pages (6 Pages main content + 2 pages for references)