This paper introduces a cross-domain and multi-dialectal stance corpus for Arabic that includes four regions in the Arab World and covers the main Arabic dialect groups. Our corpus consists of 4657 sentences manually annotated with each sentence’s stance towards a specific topic. For each region, we collected sentences related to two controversial topics. We annotated each sentence by at least two annotators to indicate if its stance favors the topic, is against it, or is neutral. Our corpus is well-balanced concerning dialect and stance. Approximately half of the sentences are in Modern Standard Arabic (MSA) for each region, and the other half is in the region’s respective dialect. We conducted several machine-learning experiments for stance detection using our new corpus. Our most successful model is the Multi-Layer Perceptron (MLP), using Unigram or TF-IDF extracted features, which yielded an F1-score of 0.66 and an accuracy score of 0.66. Compared with the most similar state-of-the-art dataset, our dataset outperformed in specific stance classes, particularly “neutral” and “against”.

The Natural Language Inference (NLI) task is a field of Natural Language Processing (NLP) in which researchers try to find ways to decide about the inference relation between two sentences. In this paper, we present an early version of an Arabic-oriented NLI system based on the word embedding technique and a deep learning model, namely Bi-LSTM. In this paper, we provide a general description of the system's various components as well as results from the parts that have already been implemented. Our primary experiments yielded positive results.

In natural language, the same meaning can be expressed by different texts. The process of determining the inference relationship occurring between a text T and a hypothesis H is called Natural Language Inference (NLI). The NLI task aims to provide a generic framework that captures, in a unifying manner, the inference across Natural Language Processing applications such as question answering, summarization, information retrieval, and machine translation. Many tasks and datasets have been created to support the development and evaluation of the ability of the NLI task in different languages. For the Arabic language, interest in this field is gradually increasing. This paper aims to provide an overview of state-of-the-art NLI approaches for Arabic, the relevant knowledge resources and the used tools in order to support a better understanding of this growing field. Moreover, this paper points to classify the proposed approaches for Arabic NLI and compare existing NLI systems.