Problem Of Named Entity Recognition Research Articles

Incorporating Entity Type-Aware and Word–Word Relation-Aware Attention in Generative Named Entity Recognition

Named entity recognition (NER) is a critical subtask in natural language processing. It is particularly valuable to gain a deeper understanding of entity boundaries and entity types when addressing the NER problem. Most previous sequential labeling models are task-specific, while recent years have witnessed the rise of generative models due to the advantage of tackling NER tasks in the encoder–decoder framework. Despite achieving promising performance, our pilot studies demonstrate that existing generative models are ineffective at detecting entity boundaries and estimating entity types. In this paper, a multiple attention framework is proposed which introduces the attention of entity-type embedding and word–word relation into the named entity recognition task. To improve the accuracy of entity-type mapping, we adopt an external knowledge base to calculate the prior entity-type distributions and then incorporate the information input to the model via the encoder’s self-attention. To enhance the contextual information, we take the entity types as part of the input. Our method obtains the other attention from the hidden states of entity types and utilizes it in self- and cross-attention mechanisms in the decoder. We transform the entity boundary information in the sequence into word–word relations and extract the corresponding embedding into the cross-attention mechanism. Through word–word relation information, the method can learn and understand more entity boundary information, thereby improving its entity recognition accuracy. We performed experiments on extensive NER benchmarks, including four flat and two long entity benchmarks. Our approach significantly improves or performs similarly to the best generative NER models. The experimental results demonstrate that our method can substantially enhance the capabilities of generative NER models.

ADAPTIVE DOMAIN-SPECIFIC NAMED ENTITY RECOGNITION METHOD WITH LIMITED DATA

The ever-evolving volume of digital information requires the development of innovative search strategies aimed at obtaining the necessary data efficiently and economically feasible. The urgency of the problem is emphasized by the growing complexity of information landscapes and the need for fast data extraction methodologies. In the field of natural language processing, named entity recognition (NER) is an essential task for extracting useful information from unstructured text input for further classification into predefined categories. Nevertheless, conventional methods frequently encounter difficulties when confronted with a limited amount of labeled data, posing challenges in real-world scenarios where obtaining substantial annotated datasets is problematic or costly. In order to address the problem of domain-specific NER with limited data, this work investigates NER techniques that can overcome these constraints by continuously learning from newly collected information on pre-trained models. Several techniques are also used for making the greatest use of the limited labeled data, such as using active learning, exploiting unlabeled data, and integrating domain knowledge. Using domain-specific datasets with different levels of annotation scarcity, the fine-tuning process of pre-trained models, such as transformer-based models (TRF) and Toc2Vec (token-to-vector) models is investigated. The results show that, in general, expanding the volume of training data enhances most models' performance for NER, particularly for models with sufficient learning ability. Depending on the model architecture and the complexity of the entity label being learned, the effect of more data on the model's performance can change. After increasing the training data by 20%, the LT2V model shows the most balanced growth in accuracy overall by 11% recognizing 73% of entities and processing speed. Meanwhile, with consistent processing speed and the greatest F1-score, the Transformer-based model (TRF) shows promise for effective learning with less data, achieving 74% successful prediction and a 7% increase in performance after expanding the training data to 81%. Our results pave the way for the creation of more resilient and efficient NER systems suited to specialized domains and further the field of domain-specific NER with sparse data. We also shed light on the relative merits of various NER models and training strategies, and offer perspectives for future research.

CLSTM-SNP: Convolutional Neural Network to Enhance Spiking Neural P Systems for Named Entity Recognition Based on Long Short-Term Memory Network

AbstractMembrane computing is a type of parallel computing system (generally called P system) abstracted from information exchange mechanisms in biological cells, tissues, or neurons, which can process data in a distributed and interpretable manner. LSTM-SNP, the first model of long short-term memory networks based on parameterized nonlinear Spiking neural P systems, was proposed recently. However, a systematic understanding and leveraging of the LSTM-SNP model to address named entity recognition (NER) and other natural language processing (NLP) tasks are still lacking. The bottleneck of the NER task lies in the scarcity of data and the vague definition of entity edges. Most approaches center on dataset handling, and there have been few attempts to address the issue in Spiking neural P (SNP) systems. This paper proposes a model named CLSTM-SNP based on the LSTM-SNP, aiming to tackle the NER problem in the field of SNP systems for the first time. First, this study employs a CNN layer to obtain character-level characteristics. Second, GloVe word vectors are utilized as word representations. Third, the research employs the LSTM-SNP to analyze textual features. We subsequently studied CLSTM-SNP’s effectiveness in addressing NER problems on CoNLL-2003 and OntoNotes 5.0 datasets and compared it to the results of five other baseline methods. Our model CLSTM-SNP achieved a macro F1-score of 89.2 $$\%$$ % on CoNLL-2003 and 75.5$$\%$$ % on OntoNotes 5.0, respectively. The performance of CLSTM-SNP and LSTM-SNP indicates a great potential for handling named entity recognition or other sequential tasks in NLP.

Citation prediction by leveraging transformers and natural language processing heuristics

In scientific papers, it is common practice to cite other articles to substantiate claims, provide evidence for factual assertions, reference limitations, and research gaps, and fulfill various other purposes. When authors include a citation in a given sentence, there are two considerations they need to take into account: (i) where in the sentence to place the citation and (ii) which citation to choose to support the underlying claim. In this paper, we focus on the first task as it allows multiple potential approaches that rely on the researcher’s individual style and the specific norms and conventions of the relevant scientific community. We propose two automatic methodologies that leverage transformers architecture for either solving a Mask-Filling problem or a Named Entity Recognition problem. On top of the results of the proposed methodologies, we apply ad-hoc Natural Language Processing heuristics to further improve their outcome. We also introduce s2orc-9K, an open dataset for fine-tuning models on this task. A formal evaluation demonstrates that the generative approach significantly outperforms five alternative methods when fine-tuned on the novel dataset. Furthermore, this model’s results show no statistically significant deviation from the outputs of three senior researchers.

Few-shot Named Entity Recognition: definition, taxonomy and research directions

Recent years have seen an exponential growth (+98% in 2022 w.r.t. the previous year) of the number of research papers in the few-shot learning field, which aims to train machine learning models with extremely limited available data. The research interest towards few-shot learning systems for Named Entity Recognition (NER) is thus at the same time increasing. NER consists in identifying mentions of pre-defined entities from unstructured text, and serves as a fundamental step in many downstream tasks, such as the construction of Knowledge Graphs, or Question Answering. The need for a NER system able to be trained with few-annotated examples comes in all its urgency in domains where the annotation process requires time, knowledge and expertise (e.g. healthcare, finance, legal), and in low-resource languages. In this survey, starting from a clear definition and description of the few-shot NER (FS-NER) problem, we take stock of the current state-of-the-art and propose a taxonomy which divides algorithms in two macro-categories according to the underlying mechanisms: model-centric and data-centric. For each category, we line-up works as a story to show how the field is moving towards new research directions. Eventually, techniques, limitations and key aspects are deeply analyzed to facilitate future studies.

AUC Maximization for Low-Resource Named Entity Recognition

Current work in named entity recognition (NER) uses either cross entropy (CE) or conditional random fields (CRF) as the objective/loss functions to optimize the underlying NER model. Both of these traditional objective functions for the NER problem generally produce adequate performance when the data distribution is balanced and there are sufficient annotated training examples. But since NER is inherently an imbalanced tagging problem, the model performance under the low-resource settings could suffer using these standard objective functions. Based on recent advances in area under the ROC curve (AUC) maximization, we propose to optimize the NER model by maximizing the AUC score. We give evidence that by simply combining two binary-classifiers that maximize the AUC score, significant performance improvement over traditional loss functions is achieved under low-resource NER settings. We also conduct extensive experiments to demonstrate the advantages of our method under the low-resource and highly-imbalanced data distribution settings. To the best of our knowledge, this is the first work that brings AUC maximization to the NER setting. Furthermore, we show that our method is agnostic to different types of NER embeddings, models and domains. The code of this work is available at https://github.com/dngu0061/NER-AUC-2T.

A survey on Named Entity Recognition — datasets, tools, and methodologies

Natural language processing (NLP) is crucial in the current processing of data because it takes into account many sources, formats, and purposes of data as well as information from various sectors of our economy, government, and private and public lives. We perform a variety of NLP operations on the text in order to complete certain tasks. One of them is NER (Named Entity Recognition). An act of recognizing and categorizing named entities that are presented in a text document is known as named entity recognition. The purpose of NER is to find references of rigid designators in the text which belong to established semantic kinds like a person, place, organization, etc. It acts as a cornerstone for many Information Extraction-related activities. In this work, we present a thorough analysis of several methodologies for NER ranging from unsupervised learning, rule-based, supervised learning, and various Deep Learning based approaches. We examine the most relevant datasets, tools, and deep learning approaches like Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Bidirectional Long Short Term Memory, Transfer learning approaches, and numerous other approaches currently being used in present-day NER problem environments and their applications. Finally, we outline the difficulties NER systems encounter and future directions.

TOE: A Grid-Tagging Discontinuous NER Model Enhanced by Embedding Tag/Word Relations and More Fine-Grained Tags

So far, discontinuous named entity recognition (NER) has received increasing research attention and many related methods have surged such as hypergraph-based methods, span-based methods, and sequence-to-sequence (Seq2Seq) methods, etc. However, these methods more or less suffer from some problems such as decoding ambiguity and efficiency, which limit their performance. Recently, grid-tagging methods, which benefit from the flexible design of tagging systems and model architectures, have shown superiority to adapt for various information extraction tasks. In this paper, we follow the line of such methods and propose a competitive grid-tagging model for discontinuous NER. We call our model TOE because we incorporate two kinds of Tag-Oriented Enhancement mechanisms into a state-of-the-art (SOTA) grid-tagging model that casts the NER problem into word-word relationship prediction. First, we design a Tag Representation Embedding Module (TREM) to force our model to consider not only word-word relationships but also word-tag and tag-tag relationships. Concretely, we construct tag representations and embed them into TREM, so that TREM can treat tag and word representations as queries/keys/values and utilize self-attention to model their relationships. On the other hand, motivated by the Next-Neighboring-Word (NNW) and Tail-Head-Word (THW) tags in the SOTA model, we add two new symmetric tags, namely Previous-Neighboring-Word (PNW) and Head-Tail-Word (HTW), to model more fine-grained word-word relationships and alleviate error propagation from tag prediction. In the experiments of three benchmark datasets, namely CADEC, ShARe13 and ShARe14, our TOE model pushes the SOTA results by about 0.83%, 0.05% and 0.66% in F1, demonstrating its effectiveness.

An Efficient Method for Deidentifying Protected Health Information in Chinese Electronic Health Records: Algorithm Development and Validation.

BackgroundWith the popularization of electronic health records in China, the utilization of digitalized data has great potential for the development of real-world medical research. However, the data usually contains a great deal of protected health information and the direct usage of this data may cause privacy issues. The task of deidentifying protected health information in electronic health records can be regarded as a named entity recognition problem. Existing rule-based, machine learning–based, or deep learning–based methods have been proposed to solve this problem. However, these methods still face the difficulties of insufficient Chinese electronic health record data and the complex features of the Chinese language.ObjectiveThis paper proposes a method to overcome the difficulties of overfitting and a lack of training data for deep neural networks to enable Chinese protected health information deidentification.MethodsWe propose a new model that merges TinyBERT (bidirectional encoder representations from transformers) as a text feature extraction module and the conditional random field method as a prediction module for deidentifying protected health information in Chinese medical electronic health records. In addition, a hybrid data augmentation method that integrates a sentence generation strategy and a mention-replacement strategy is proposed for overcoming insufficient Chinese electronic health records.ResultsWe compare our method with 5 baseline methods that utilize different BERT models as their feature extraction modules. Experimental results on the Chinese electronic health records that we collected demonstrate that our method had better performance (microprecision: 98.7%, microrecall: 99.13%, and micro-F1 score: 98.91%) and higher efficiency (40% faster) than all the BERT-based baseline methods.ConclusionsCompared to baseline methods, the efficiency advantage of TinyBERT on our proposed augmented data set was kept while the performance improved for the task of Chinese protected health information deidentification.

Nested Named Entity Recognition: A Survey

With the rapid development of text mining, many studies observe that text generally contains a variety of implicit information, and it is important to develop techniques for extracting such information. Named Entity Recognition (NER), the first step of information extraction, mainly identifies names of persons, locations, and organizations in text. Although existing neural-based NER approaches achieve great success in many language domains, most of them normally ignore the nested nature of named entities. Recently, diverse studies focus on the nested NER problem and yield state-of-the-art performance. This survey attempts to provide a comprehensive review on existing approaches for nested NER from the perspectives of the model architecture and the model property, which may help readers have a better understanding of the current research status and ideas. In this survey, we first introduce the background of nested NER, especially the differences between nested NER and traditional (i.e., flat) NER. We then review the existing nested NER approaches from 2002 to 2020 and mainly classify them into five categories according to the model architecture, including early rule-based, layered-based, region-based, hypergraph-based, and transition-based approaches. We also explore in greater depth the impact of key properties unique to nested NER approaches from the model property perspective, namely entity dependency, stage framework, error propagation, and tag scheme. Finally, we summarize the open challenges and point out a few possible future directions in this area. This survey would be useful for three kinds of readers: (i) Newcomers in the field who want to learn about NER, especially for nested NER. (ii) Researchers who want to clarify the relationship and advantages between flat NER and nested NER. (iii) Practitioners who just need to determine which NER technique (i.e., nested or not) works best in their applications.

A Survey on Deep Learning for Named Entity Recognition

Named entity recognition (NER) is the task to identify mentions of rigid designators from text belonging to predefined semantic types such as person, location, organization etc. NER always serves as the foundation for many natural language applications such as question answering, text summarization, and machine translation. Early NER systems got a huge success in achieving good performance with the cost of human engineering in designing domain-specific features and rules. In recent years, deep learning, empowered by continuous real-valued vector representations and semantic composition through nonlinear processing, has been employed in NER systems, yielding stat-of-the-art performance. In this paper, we provide a comprehensive review on existing deep learning techniques for NER. We first introduce NER resources, including tagged NER corpora and off-the-shelf NER tools. Then, we systematically categorize existing works based on a taxonomy along three axes: distributed representations for input, context encoder, and tag decoder. Next, we survey the most representative methods for recent applied techniques of deep learning in new NER problem settings and applications. Finally, we present readers with the challenges faced by NER systems and outline future directions in this area.

Movie Aspects Identification Model for Aspect Based Sentiment Analysis

Aspect Based Sentiment Analysis techniques have been applied in several application domains. From the last two decades, these techniques have been developed mostly for product and service application domains. However, very few aspect-based sentiment techniques have been proposed for the movie application domain. Moreover, these techniques only mine specific aspects (Script, Director, and Actor) of a movie application domain, nevertheless, the movie application domain is more complex than the product and service application domain. Since, it contains NER (Named Entity Recognition) problem and it cannot be ignored, since there is an opinion often associated with it. Consequently, in this paper MAIM (Movie Aspect Identification Model) is proposed that can extract not only movie specific aspects, also identifies NEs (Named Entities) such as Person Name and Movie Title. The three main contributions are 1) the identification of infrequent aspects, 2) the identification of NE (named entity) in movie application domain, 3) identifying N-gram opinion words as an entity. MAIM incorporates the BiLSTM-CRF hybrid technique and is implemented on the movie application domain having precision 89.9%, recall 88.9% and f1-measure 89.4%. The experimental results show that MAIM performs better than baseline models CRF and LSTM-CRF.

Entity-aware capsule network for multi-class classification of big data: A deep learning approach

Named entity recognition (NER) is one of the most challenging natural language processing (NLP) tasks, as its performance is related to constantly evolving languages and dependency on expert (human) annotation. The diverse and dynamic content on the web significantly raises the need for a more generalized approach—one that is capable of correctly classifying terms in a corpus and feeding subsequent NLP tasks, such as machine translation, query expansion, and many other applications. Although extensively researched in recent times, the variety of public corpora available nowadays provides room for new and more accurate methods to tackle the NER problem. This paper presents a novel method that uses deep learning techniques based on the capsule network architecture for predicting entities in a corpus. This type of network groups neurons into so-called capsules to detect specific features of an object without reducing the original input unlike convolutional neural networks and their ‘max-pooling’ strategy. Our extensive evaluation on several benchmarked datasets demonstrates how competitive our method is in comparison with state-of-the-art techniques and how the usage of the proposed architecture may represent a significant benefit to further NLP tasks, especially in cases where experts are needed. Also, we explore NER using a theoretical framework that leverages big data for security. For the sake of reproducibility, we make the codebase open-source22https://github.com/amitkumarj441/CapsRoute_NER..

Few-Shot Named Entity Recognition via Meta-Learning

Few-shot learning under the <inline-formula><tex-math notation="LaTeX">$N$</tex-math></inline-formula> -way <inline-formula><tex-math notation="LaTeX">$K$</tex-math></inline-formula> -shot setting (i.e., <inline-formula><tex-math notation="LaTeX">$K$</tex-math></inline-formula> annotated samples for each of <inline-formula><tex-math notation="LaTeX">$N$</tex-math></inline-formula> classes) has been widely studied in relation extraction (e.g., FewRel) and image classification (e.g., Mini-ImageNet). Named entity recognition (NER) is typically framed as a sequence labeling problem where the entity classes are inherently entangled together because the entity number and classes in a sentence are not known in advance, leaving the <inline-formula><tex-math notation="LaTeX">$N$</tex-math></inline-formula> -way <inline-formula><tex-math notation="LaTeX">$K$</tex-math></inline-formula> -shot NER problem so far unexplored. In this paper, we first formally define a more suitable <inline-formula><tex-math notation="LaTeX">$N$</tex-math></inline-formula> -way <inline-formula><tex-math notation="LaTeX">$K$</tex-math></inline-formula> -shot setting for NER. Then we propose <small>FewNER</small> , a novel meta-learning approach for few-shot NER. <small>FewNER</small> separates the entire network into a task-independent part and a task-specific part. During training in <small>FewNER</small> , the task-independent part is meta-learned across multiple tasks and the task-specific part is learned for each individual task in a low-dimensional space. At test time, <small>FewNER</small> keeps the task-independent part fixed and adapts to a new task via gradient descent by updating only the task-specific part, resulting in it being less prone to overfitting and more computationally efficient. Compared with pre-trained language models (e.g., BERT and ELMo) which obtain the transferability in an implicit manner (i.e., relying on large-scale corpora), <small>FewNER</small> explicitly optimizes the capability of “learning to adapt quickly” through meta-learning. The results demonstrate that <small>FewNER</small> achieves state-of-the-art performance against nine baseline methods by significant margins on three adaptation experiments (i.e., intra-domain cross-type, cross-domain intra-type and cross-domain cross-type).

Named entity recognition: a semi-supervised learning approach

Named entity recognition (NER) application development for under-resourced (i.e. NLP resource) language is usually obstructed by lack of named entity tagged dataset and this led to performance deterioration. Similarly, in Amharic language getting annotated training dataset for named entity recognition problem is extortionate, though an enormous amount of untagged data is easily accessible. Fortunately, the performance of NER possibly be boosted via encompassing a few labeled data with an oversized collection of unlabeled data. Based on this premise, this paper tend to investigate graph-based label propagation algorithm for the Amharic NER problem, a simple semi-supervised, iterative algorithm, to propagate labels through the dataset. In addition, it is aimed at making a rigorous comparison with expectation–maximization with semi-supervised learning approaches. The experiment reveals, label propagation based NER achieves superior performance compared to expected maximization using a few labeled training data. Since expectation maximization algorithm demands a moderate labeled example to be learned, meant very few labeled examples are not enough to generate adequate parameters for recognition of named entities, consequently it couldn’t perform great as the label propagation algorithm.

Boundary Enhanced Neural Span Classification for Nested Named Entity Recognition

Named entity recognition (NER) is a well-studied task in natural language processing. However, the widely-used sequence labeling framework is usually difficult to detect entities with nested structures. The span-based method that can easily detect nested entities in different subsequences is naturally suitable for the nested NER problem. However, previous span-based methods have two main issues. First, classifying all subsequences is computationally expensive and very inefficient at inference. Second, the span-based methods mainly focus on learning span representations but lack of explicit boundary supervision. To tackle the above two issues, we propose a boundary enhanced neural span classification model. In addition to classifying the span, we propose incorporating an additional boundary detection task to predict those words that are boundaries of entities. The two tasks are jointly trained under a multitask learning framework, which enhances the span representation with additional boundary supervision. In addition, the boundary detection model has the ability to generate high-quality candidate spans, which greatly reduces the time complexity during inference. Experiments show that our approach outperforms all existing methods and achieves 85.3, 83.9, and 78.3 scores in terms of F1 on the ACE2004, ACE2005, and GENIA datasets, respectively.

Fine Grained Named Entity Recognition via Seq2seq Framework

Fine-grained Named entity recognition (NER) is crucial to natural language processing (NLP) applications like relation extraction and knowledge graph construction. Most existing fine-grained NER systems suffer from inefficiency problem as they use manually annotated training datasets. To address such issue, our NER system could automatically generate datasets from Wikipedia in distant supervision paradigm through mapping hyperlinks in Wikipedia documents to Freebase. In addition, previous NER models can not effectively process fine-grained labels with more than 100 types. So we introduce a ‘BIO’ tagging strategy which can identify the position and type attributes simultaneously. Such tagging scheme transfers NER problem into a sequence-to-sequence (seq2seq) based issue. We propose a seq2seq framework to comprehend the input sentence in a comprehensive way. Specifically, we adopt a Bi-LSTM as the encoder to equally process the past and future information of the input. Then we add a self-attention mechanism to handle the long-term dependency problem in a long sequence. When classifying the entity tags, we choose CRF model as it adds more constraints to avoid position logical problem. Experiments are performed on large-scale datasets for fine-grained NER tasks. Experimental results verify the effectiveness of FSeqC, and it outperforms other state-of-the-art alternatives consistently and significantly.

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%.

An Improved Word Representation for Deep Learning Based NER in Indian Languages

Named Entity Recognition (NER) is the process of identifying the elementary units in a text document and classifying them into predefined categories such as person, location, organization and so forth. NER plays an important role in many Natural Language Processing applications like information retrieval, question answering, machine translation and so forth. Resolving the ambiguities of lexical items involved in a text document is a challenging task. NER in Indian languages is always a complex task due to their morphological richness and agglutinative nature. Even though different solutions were proposed for NER, it is still an unsolved problem. Traditional approaches to Named Entity Recognition were based on the application of hand-crafted features to classical machine learning techniques such as Hidden Markov Model (HMM), Support Vector Machine (SVM), Conditional Random Field (CRF) and so forth. But the introduction of deep learning techniques to the NER problem changed the scenario, where the state of art results have been achieved using deep learning architectures. In this paper, we address the problem of effective word representation for NER in Indian languages by capturing the syntactic, semantic and morphological information. We propose a deep learning based entity extraction system for Indian languages using a novel combined word representation, including character-level, word-level and affix-level embeddings. We have used ‘ARNEKT-IECSIL 2018’ shared data for training and testing. Our results highlight the improvement that we obtained over the existing pre-trained word representations.

Arabic named entity recognition via deep co-learning

Named entity recognition (NER) is an important natural language processing (NLP) task with many applications. We tackle the problem of Arabic NER using deep learning based on Arabic word embeddings that capture syntactic and semantic relationships between words. Deep learning has been shown to perform significantly better than other approaches for various NLP tasks including NER. However, deep-learning models also require a significantly large amount of training data, which is highly lacking in the case of the Arabic language. To remedy this, we adopt the semi-supervised co-training approach to the realm of deep learning, which we refer to as deep co-learning. Our deep co-learning approach makes use of a small amount of labeled data, which is augmented with partially labeled data that is automatically generated from Wikipedia. Our approach relies only on word embeddings as features and does not involve any additional feature engineering. Nonetheless, when tested on three different Arabic NER benchmarks, our approach consistently outperforms state-of-the-art Arabic NER approaches, including ones that employ carefully-crafted NLP features. It also consistently outperforms various baselines including purely-supervised deep-learning approaches as well as semi-supervised ones that make use of only unlabeled data such as self-learning and the traditional co-training approach.