Search

As of late, various deep learning techniques and methods have shown their superiority to feature-based and shallow learning techniques in the field of open-domain question–answering systems (OpenQAS). However, only a few works adopted these techniques to build Arabic OpenQAS that can extract exact answers from large information sources (e.g., Wikipedia). In addition, no available Arabic OpenQAS integrated a module to identify duplicate questions to accelerate response time and reduce computation cost. In this paper, we propose an Arabic OpenQAS (named DAQAS) based on deep learning methods. It consists of three components: (1) Dense Duplicate Question Detection which returns answers to questions that already have been answered; (2) Retriever based on BM25 and Query Expansion by neural text generation; and (3) Reader able to extract exact answers given a question and the retrieved passages that probably contains the answer. All components of our system integrate deep learning models, specially transformers-based techniques, which have scored state-of-the-art in different NLP fields. We performed several experiments with publicly available question answering datasets to show the effectiveness of our system. DAQAS obtained promising results and scored 21.77% Exact Match and 54.71% F1 score when using only top 5 retrieved passages.

Question Answering Systems (QAS) are rising solutions providing exact and precise answers to natural questions. Duplicate Question Detection (DQD), which aims to reuse previous answers, has shown its ability to improve user experience and reduce significantly the response time. However, few Arabic QAS integrate solutions able to detect duplicate questions in their workflow. In this paper, we build a DQD method based on contextual word representation, question classification and forward/backward structured self attention. First, we extract contextual word representation Embeddings from Language Models (ELMo) to map questions into a vector space. Next, we train two models to classify question embedding according to two taxonomies: Hamza et al. and Li & Roth. Then, we introduce a class label matching step to filter out questions that have different class labels. Finally, we propose a Bidirectional Attention Bidirectional LSTM (BiAttention BiLSTM) model that focuses only on keywords to predict whether a question pair is a duplicate or not. We also apply a data augmentation strategy based on symmetry, reflexivity, and transitivity relations to improve the generalization of our model. Various experimentations are performed to evaluate the impact of question classification and pre-processing step on DQD model. The obtained results show that our model achieves good performances as compared to the baseline results.

The unability of search engines to retrieve precise answer for a given question leads research teams to build question answering systems (QAS). These systems provide exact answers of questions formulated in natural languages. Question classification is a crucial task for QAS since finding the correct answer type increases the performance of this latter. The questions taxonomy plays an important role in question classification. A broad range of taxonomies are proposed; most of these are not designed for Arabic questions. The contribution of the paper is twofold. First, we build a taxonomy for open domain Arabic questions. Second, we propose an efficient method for classifying Arabic questions. The basic idea consists of two stages: first, we compute representation of questions according to continuous distributed representation of words which allows to capture syntactic and semantic relations between words. Then, we apply a machine learning approach to classify questions into seven types or categories. We carried out several experiments and compared the proposed method with different state of arts Arabic question classification methods. Experimental results show that the proposed method achieves 90% in terms of accuracy.