An Accurate Arabic Root-Based Lemmatizer for Information Retrieval Purposes
This addresses the problem of Arabic information retrieval for NLP practitioners by providing a more accurate lemmatizer, though it is incremental as it builds on existing language resources.
The paper tackles the lack of lemma-level analysis in Arabic NLP by proposing a non-statistical Arabic lemmatizer for information retrieval, achieving up to 94.8% accuracy in POS tagging and 89.15% accuracy on first-seen documents compared to 76.7% for a state-of-the-art model.
In spite of its robust syntax, semantic cohesion, and less ambiguity, lemma level analysis and generation does not yet focused in Arabic NLP literatures. In the current research, we propose the first non-statistical accurate Arabic lemmatizer algorithm that is suitable for information retrieval (IR) systems. The proposed lemmatizer makes use of different Arabic language knowledge resources to generate accurate lemma form and its relevant features that support IR purposes. As a POS tagger, the experimental results show that, the proposed algorithm achieves a maximum accuracy of 94.8%. For first seen documents, an accuracy of 89.15% is achieved, compared to 76.7% of up to date Stanford accurate Arabic model, for the same, dataset.