Neural Arabic Question Answering

By Hussein Mozannar, Karl El Hajal, Elie Maamary, Hazem M. Hajj. 2019

172 citations recorded by the source corpus.

This paper tackles the problem of open domain factual Arabic question answering (QA) using Wikipedia as our knowledge source. This constrains the answer of any question to be a span of text in Wikipedia. Open domain QA for Arabic entails three challenges: annotated QA datasets in Arabic, large scale efficient information retrieval and machine reading comprehension. To deal with the lack of Arabic QA datasets we present the Arabic Reading Comprehension Dataset (ARCD) composed of 1,395 questions posed by crowdworkers on Wikipedia articles, and a machine translation of the Stanford Question Answering Dataset (Arabic-SQuAD). Our system for open domain question answering in Arabic (SOQAL) is based on two components: (1) a document retriever using a hierarchical TF-IDF approach and (2) a neural reading comprehension model using the pre-trained bi-directional transformer BERT. Our experiments on ARCD indicate the effectiveness of our approach with our BERT-based reader achieving a 61.3 F1 score, and our open domain system SOQAL achieving a 27.6 F1 score.

Subfields: Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages (2020, methodology): “…et al., 2018; Lim et al., 2019), a semi-automatic Italian translation of SQuAD (Croce et al., 2018), ARCD—an Arabic reading comprehension dataset (Mozannar et al., 2019), a Hindi-English parallel dataset in a SQuAD-like setting (Gupta et al., 2018), and a Chinese–English dataset focused on…”
MLQA: Evaluating Cross-lingual Extractive Question Answering (2019, background): “The second, generalised cross-lingual transfer (G-XLT) requires models to answer questions where the question and context language is different , e.g. questions in Hindi and contexts in Arabic, a setting possible because MLQA is highly parallel.”
AraBERT: Transformer-based Model for Arabic Language Understanding (2020, methodology): “Table 2: Example of an erroneous results from the ARCD test set: the only difference is the preposition “ ú(cid:10)(cid:9)¯ -”
ARBERT & MARBERT: Deep Bidirectional Transformers for Arabic (2020, methodology): “We use ARCD (Mozannar et al., 2019) and the three human translated Arabic test sections of the XTREME benchmark (Hu et al., 2020): MLQA (Lewis et al., 2020), XQuAD (Artetxe et al., 2020), and TyDi QA (Artetxe et al., 2020).”
MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answering (2020, background): “For Korean and Arabic the best F1 score is only 6% higher than the lower bound score of 32 .”
Human or Machine? A Survey on Machine-Generated Text Detection (2026, unknown): “The ‘‘Large Corpus’’ contains 43,958 instances, comprising 21,979 HWT and 21,979 MGT. HWT are gathered from three existing sources, Arabic-SQuAD [64], TyDiQA [65], and MLQA [66].”