Arabic Named Entity Recognition Research Articles

A Benchmark Evaluation of Multilingual Large Language Models for Arabic Cross-Lingual Named-Entity Recognition

Multilingual large language models (MLLMs) have demonstrated remarkable performance across a wide range of cross-lingual Natural Language Processing (NLP) tasks. The emergence of MLLMs made it possible to achieve knowledge transfer from high-resource to low-resource languages. Several MLLMs have been released for cross-lingual transfer tasks. However, no systematic evaluation comparing all models for Arabic cross-lingual Named-Entity Recognition (NER) is available. This paper presents a benchmark evaluation to empirically investigate the performance of the state-of-the-art multilingual large language models for Arabic cross-lingual NER. Furthermore, we investigated the performance of different MLLMs adaptation methods to better model the Arabic language. An error analysis of the different adaptation methods is presented. Our experimental results indicate that GigaBERT outperforms other models for Arabic cross-lingual NER, while language-adaptive pre-training (LAPT) proves to be the most effective adaptation method across all datasets. Our findings highlight the importance of incorporating language-specific knowledge to enhance the performance in distant language pairs like English and Arabic.

Named Entity Recognition of Tunisian Arabic Using the Bi-LSTM-CRF Model

Named Entity Recognition (NER) is an NLP field that deals with recognizing and classifying entities in written text. Most Arabic NER research studies discuss the Arabic NER challenge for the Modern Standard Arabic (MSA) language. However, the presence of dialectal Arabic textual resources in social media, blogs, TV shows, etc. is increasingly progressive. Therefore, the treatment of named entities is rapidly becoming a necessity, particularly for dialectal Arabic. In this paper, we are interested in the collection and annotation of a corpus as well as the realization of a NER system for Tunisian Arabic (TA), named TUNER. To the best of the researchers’ knowledge, this is the first study that uses the suggested method for this purpose. In the present study, we adopt a hybrid method based on a Bi-LSTM-CRF model and a rule-based method. The proposed TUNER system yields an F-measure of 91.43%. This is an interesting improvement over comparable related work dialectal Arabic NER systems.

A Survey on Arabic Named Entity Recognition: Past, Recent Advances, and Future Trends

A Survey on Arabic Named Entity Recognition: Past, Recent Advances, and Future Trends

Advancements in Arabic Named Entity Recognition: A Comprehensive Review

Advancements in Arabic Named Entity Recognition: A Comprehensive Review

Arabic NER Evaluation: Pre-Trained Models via Contrastive Learning vs. LLM Few-Shot Prompting

Developing Natural Language Processing (NLP) tools for the Arabic language and its dialects is very challenging. Named Entity Recognition (NER) is one of these challenges, which serves as the core component in many NLP systems such as information extraction, question answering, machine translation and knowledge graph building. This paper sheds light on applying diferent approaches for Arabic NER (Flat and Nested) using a large and rich Arabic NER corpus, Wojood dataset, which consists of about 550K tokens annotated with 21 entity types. First, we apply the Wojood base model, AraBERTv2, along with various other Arabic BERT models such as MARBERTv2, CaMelBert, mBert, ..etc. Next, we utilize the Bi-Encoder Contrastive Learning (CL) approach, a framework developed by Microsoft, which maps candidate text spans and entity types into the same vector representation space. The primary challenge in this approach is distinguishing non-entity spans from entity mentions. This approach could achieve F1 score 91.25% for Flat and 91.40% for Nested NER. Additionally, for evaluating the predicted NER, we employ Few-Shot prompting on LLaMA, and GPT-3.5 using refined prompt-based strategy. Our findings reveal that LLaMA outperforms GPT3.5.

Improving Arabic Named Entity Recognition with a Modified Transformer Encoder

This article investigates the use of a transformer encoder for Arabic Named Entity Recognition (NER). The classic transformer that was originally proposed for machine translation adopts the absolute sinusoidal position embedding which is aware of distance but unfortunately is not aware of the directionality. However, in the NER task, both distance and orientation are crucial. Therefore, in this study, instead of using absolute sinusoidal position encoding, we employ relative positional encoding and incorporate the directionality information in our NER model. More specifically, our proposed model uses Bidirectional Long Short-Term Memory (BiLSTM) for encoding every input token. Then, the output of the encoder is fed to the multi-head attention where both the distance and directionality information are incorporated. The decoder layer with a simple fully connected layer takes as input, the result of the attention layer, and the prediction layer with Conditional Random Fields (CRF) predicts the tag of each token. We validate our proposed approach on two merged public datasets, namely, ANER corp and AQMAR. Our experiment results demonstrate significant improvements when compare to the vanilla Transformer with absolute sinusoidal position encoding while achieving a state-of-the-art result on a merged two Arabic public datasets.

A benchmark for evaluating Arabic word embedding models

AbstractModelling the distributional semantics of such a morphologically rich language as Arabic needs to take into account its introflexive, fusional, and inflectional nature attributes that make up its combinatorial sequences and substitutional paradigms. To evaluate such word distributional models, the benchmarks that have been used thus far in Arabic have mimicked those in English. This paper reports on a benchmark that we designed to reflect linguistic patterns in both Contemporary Arabic and Classical Arabic, the first being a cover term for written and spoken Modern Standard Arabic, while the second for pre-modern Arabic. The analogy items we included in this benchmark are chosen in a transparent manner such that they would capture the major features of nouns and verbs; derivational and inflectional morphology; high-, middle-, and low-frequency patterns and lexical items; and morphosemantic, morphosyntactic, and semantic dimensions of the language. All categories included in this benchmark are carefully selected to ensure proper representation of the language. The benchmark consists of 45 roots of the trilateral, all-consonantal, and semivowel-inclusive types; six morphosemantic patterns (’af‘ala; ifta‘ala; infa‘ala; istaf‘ala; tafa‘‘ala; and tafā‘ala); five derivations (the verbal noun, active participle, and the contrasts in Masculine-Feminine; Feminine-Singular-Plural; Masculine-Singular-Plural); and morphosyntactic transformations (perfect and imperfect verbs conjugated for all pronouns); and lexical semantics (synonyms, antonyms, and hyponyms of nouns, verbs, and adjectives), as well as capital cities and currencies. All categories include an equal proportion of high-, medium-, and low-frequency items. For the purpose of validating the proposed benchmark, we developed a set of embedding models from different textual sources. Then, we tested them intrinsically using the proposed benchmark and extrinsically using two natural language processing tasks: Arabic Named Entity Recognition and Text Classification. The evaluation leads to the conclusion that the proposed benchmark is truly reflective of this morphologically rich language and discriminatory of word embeddings.

Boosting Arabic Named Entity Recognition with K-Fold Cross Validation on LSTM and Bi-LSTM Models

Named-Entity-Recognition(NER) is one of the most important Information-Extraction (IE) use cases, whichis used to improve the performance of Natural Languages Processing (NLP) tasks,such as Relation-Extraction (RE), Question-Answering (QA). Recently, Arabic NER is tackled in differentways by researchers. In this study, we assess the performance of two widelyused models, namely, LSTM and Bi-LSTM on the NER task in the Arabic languageand perform a comparative study between these models. In contrast to thetraditional data partition technique widely used during the training, we employthe technique of k-fold cross-validation to improve the performance of eachmodel. The experimental results reveal that the performance of all models isimproved when k-fold cross-validation is applied. Additionally, according toour experiment results, the Bi-LSTM model outperforms the LSTM model in termsof our evaluation metric. We achieve the best F1 score of 94.17% withCNN-Bi-LSTM-CRF. An ablation study on k-fold cross-validation demonstrates thatthe F1 score increased from 87.28 to 94.17%.

Towards an approach based on particle swarm optimization for Arabic named entity recognition on social media

Named entity recognition is an essential task for various applications related to natural language processing (NLP). It aims to retrieve a variety of named entities (NEs) from text and categorize them according to predetermined target categories. In many cases, using the entire feature set can be time-consuming and negatively impact the performance. Moreover, it is challenging to find the relevant subsets of features for a particular task due to the high number. The feature selection technique is an unsupervised process for selecting informative features by creating a new subset of informative features. This technique is used to enhance the underlying algorithm's performance. This article implements an effective feature selection algorithm using particle swarm optimization (PSO) to identify and classify the Arabic NEs in the text from social media. PSO is a search algorithm that utilizes a population of particles in a multidimensional space. The proposed method is evaluated using two publicly available Arabic Dialect social media datasets. It is demonstrated through comparisons with both baselines and previous models that the new approach achieves significant accuracy with considerably reduced feature sets in all parameters.

Arabic named entity recognition in social media based on BiLSTM-CRF using an attention mechanism

Named Entity Recognition (NER) is a vitally important task of Natural Language Processing (NLP), which aims at finding named entities in natural language text and classifying them into predefined categories such as persons (PER), places (LOC), organizations (ORG), and so on. In the Arabic context, the current NER approaches based on deep learning are mainly based on word embedding or character-level embedding as input. However, using a single granularity representation has problems with out-of-vocabulary (OOV), word embedding errors, and relatively simple semantic content. This paper presents a multi-headed self-attention mechanism implemented in the BiLSTM-CRF neural network structure to recognize Arabic named entities on social media using two embeddings. Unlike other state-of-the-art approaches, this approach combines character and word embedding at the embedding layer, and the attention mechanism calculates the similarity over the entire sequence of characters and captures local context information. The proposed approach better recognized NEs in Dialect Arabic, reaching an F1 value of 74.15% on Darwish’s dataset (a publicly available Arabic NER benchmark for social media). According to our knowledge, our findings outperform the current state-of-the-art models for Arabic Named Entity Recognition on social media.

New approach for Arabic named entity recognition on social media based on feature selection using genetic algorithm

Many features can be extracted from the massive volume of data in different types that are available nowadays on social media. The growing demand for multimedia applications was an essential factor in this regard, particularly in the case of text data. Often, using the full feature set for each of these activities can be time-consuming and can also negatively impact performance. It is challenging to find a subset of features that are useful for a given task due to a large number of features. In this paper, we employed a feature selection approach using the genetic algorithm to identify the optimized feature set. Afterward, the best combination of the optimal feature set is used to identify and classify the Arabic named entities (NEs) based on support vector. Experimental results show that our system reaches a state-of-the-art performance of the Arab NER on social media and significantly outperforms the previous systems.

Classical Arabic Named Entity Recognition Using Variant Deep Neural Network Architectures and BERT

Recurrent Neural Networks (RNNs) and transformers are deep learning models that have achieved remarkable success in several Natural Language Processing (NLP) tasks since they do not rely on handcrafted features nor enormous knowledge resources. Named Entity Recognition (NER) is an essential NLP task that is used in many applications such as information retrieval, question answering, and machine translation. NER aims to locate, extract, and classify named entities into predefined categories such as person, organization and location. Arabic NER is considered a challenging task because of the complexity and the unique characteristics of Arabic. Most of the previous research on deep learning based-Arabic NER focused on Modern Standard Arabic and Dialectal Arabic, which are different variations from Classical Arabic. In this paper, we investigate deep learning-based Classical Arabic NER using different deep neural network architectures and a BERT based contextual language model that is trained on general domain Arabic text. We propose two RNN-based models by fine-tunning the pretrained BERT language model to recognize and classify named entities from Classical Arabic. The pre-trained BERT contextual language model representations were used as input features to a BGRU/BLSTM model and were fine-tuned using a Classical Arabic NER dataset. In addition, we explore variant architectures of the proposed BERT-BGRU/BLSTM-CRF models. Experimentations showed that the BERT-BGRU-CRF model outperformed the other models by achieving an F-measure of 94.76% on the CANERCorpus. To the best of our knowledge, this is the first work that aims to recognize named entities in Classical Arabic using deep learning.

Data Augmentation Techniques on Arabic Data for Named Entity Recognition

Much research has been conducted to apply data augmentation techniques (DA), i.e., transformations to a given training set to produce more data synthetically. While DA is often used in computer vision and speech recognition, it is not very common in Natural Language Processing, especially in the Named Entity Recognition (NER) task, i.e., identifying named entities. To the best of our knowledge, it is also not applied in NER on the challenging Code-Switching (CS) data, which is text containing more than one language in the same sentence. This paper presents several practical and easy-to-implement data augmentation techniques to improve the Arabic NER and especially on CS data based on word embedding substitution, a modified version of the Easy Data Augmentation technique, and back-translation. We demonstrate that the proposed methods boost the performance of the NER task on CS data through several experiments on an available AR-EN CS data-set with an increase of F-score equal to 1.5%. The proposed DA methods also eliminate the time and effort of collecting and labeling new data for low resources NER tasks.

Automatic Arabic Named Entity Extraction and Classification for Information Retrieval

This article tries to explain our rule-based Arabic Named Entity recognition (NER) and classification system. It is based on lists of classified proper names (PN) and particularly on syntactico-semantic patterns resulting in fine classification of Arabic NE. These patterns use syntactico-semantic combination of morpho-syntactic and syntactic entities. It also uses lexical classification of trigger words and NE extensions. These linguistic data are essential not only to name entity extraction but also to the taxonomic classification and to determining the NE frontiers. Our method is also based on the contextualisation and on the notion of NE class attributes and values. Inspired from X-bar theory and immediate constituents, we built a rule-based NER system composed of five levels of syntactico-semantic combination. We also show how the fine NE annotations in our system output (XML database) is exploited in information retrieval and information extraction.

Recognition System for Libyan Entity Names

Named Entity Recognition (NER) is a computational linguistic concept that is used to find and classify appropriate nouns in a text such as person names, geographical locations, and organizations. Such a concept is fundamental in the field of natural language processing. In Libya, many private and public institutions suffer from using the proper translation of entity names from Arabic language into English. Therefore, in this paper, we are concerned with analyzing Arabic articles to extract and recognize entity names. A recognition system is developed for recognizing names of persons, academic institutions, and cities in Libya. At first, a training corpus and dictionaries are built for the intended entity names in this research. Then, the aspects of the entity names are studied, and their patterns and rules are designed. Then, the implementation is performed using Nooj linguistic language. The recognition of person names and Libyan cities and academic institutions was carried out. Statistics showed the frequencies of the appearance rate of person names, academic institutions, and cities in our training corpus. The obtained results are promised and met the research goals for tackling the problem of Arabic named entity recognition.

Extracting Arabic Composite Names Using Genitive Principles of Arabic Grammar

Named Entity Recognition (NER) is a basic prerequisite of using Natural Language Processing (NLP) for information retrieval. Arabic NER is especially challenging as the language is morphologically rich and has short vowels with no capitalisation convention. This article presents a novel rule-based approach that uses linguistic grammar-based techniques to extract Arabic composite names from Arabic text. Our approach uniquely exploits the genitive Arabic grammar rules; in particular, the rules regarding the identification of definite nouns (معرفة) and indefinite nouns (نكرة) to support the process of extracting composite names. Based on domain knowledge and Arabic Genitive Rules (AGR), the developed approach formalises a set of syntactical rules and linguistic patterns that initially use genitive patterns to classify definiteness within phrases and then extracts proper composite names from the unstructured text. The developed novel approach does not place any constraints on the length of the Arabic composite name and our initial experimentation demonstrated high recall and precision results when the NER algorithm was applied to a financial domain corpus.

A Recent Survey of Arabic Named Entity Recognition on Social Media

A Recent Survey of Arabic Named Entity Recognition on Social Media

A Comparison between Conditional Random Field and Structured Support Vector Machine for Arabic Named Entity Recognition

The Named Entity Recognition (NER) is an integrated task in many NLP applications such as machine translation, Information extraction and question answering. Arabic is one of the authorised spoken languages in the united nation. Currently, there is much Arabic information on the internet, so, nowadays the need for tools which process this information becomes significant. In this study, we have examined the impact of the conditional random field and the structured support vector machine in the task of Arabic NER. The structured support vector machine is the first time to be applied in the Arabic name entity recognition. Our proposed system has three stages: Preprocessing, extracting features and building model. We have used simple features like the bag of words in the [-1,1] window, the bag of part of speech tag in the [-1,1] window to enable our system to detect the multi-words entities. Also, we have tried to enhance the Stanford part of speech tagger to enhance the tagger output tags, which enabled our system to differentiate between the name entities from the non-entities. In addition, we have employed the binary features of: Is a person, is a prename, is a pre-location, is a location and is an organization. Our system has been trained and tested on part of ANER Crop. The results have proved that the conditional random field-based Arabic NER system outperforms the structured support vector machine-based Arabic NER using the same features set.

Transfer Learning for Arabic Named Entity Recognition With Deep Neural Networks

The vast amount of unstructured data spread on a daily basis rises the need for developing effective information retrieval and extraction methods. Named Entity Recognition is a challenging classification task for structuring data into pre-defined labels, and is even more complicated when being applied on the Arabic language due to its special traits and complex nature. This article presents a novel Deep Learning approach for Standard Arabic Named Entity Recognition that proved its out-performance when being compared to previous works. The main aim of building a new model is to provide better fine-grained results for use in the Natural Language Processing fields. In our proposed methodology we utilized transfer learning with deep neural networks to build a Pooled-GRU model combined with the Multilingual Universal Sentence Encoder. Our proposed model scored about 17% enhancement when being compared to previous work.

Bidirectional Encoder–Decoder Model for Arabic Named Entity Recognition

Sequence labeling models with recurrent neural network variants, such as long short-term memory (LSTM) and gated recurrent units, show promising performance in several natural language processing tasks, such as named entity recognition (NER). Most current models use unidirectional decoders, which reason only about the past and remain limited to retaining future contexts while generating predictions. Therefore, these models suffer from their generation of unbalanced outputs. Moreover, most existing NER models utilize word embeddings for capturing similarities between words but sustain when handling previously unobserved or infrequently used words. We propose a bidirectional encoder–decoder model for addressing the problem of Arabic NER on the basis of recent work in deep learning, in which the encoder and decoder are bidirectional LSTMs. In addition to word-level embeddings, character-level embeddings are adopted, and they are combined via an embedding-level attention mechanism. Our model can dynamically determine the information that must be utilized from a word- or character-level component through this attention mechanism. Experimental results on the ANERCorp and AQMAR datasets show that the model with a bi-encoder–decoder network and embedding attention layer achieves a high F-score measure of approximately 92%.