NER

The MNIST database (Modified National Institute of Standards and Technology database) is a large collection of handwritten digits. It has a training set of 60,000 examples, and a test set of 10,000 examples. It is a subset of a larger NIST Special Database 3 (digits written by employees of the United States Census Bureau) and Special Database 1 (digits written by high school students) which contain monochrome images of handwritten digits. The digits have been size-normalized and centered in a fixed-size image. The original black and white (bilevel) images from NIST were size normalized to fit in a 20x20 pixel box while preserving their aspect ratio. The resulting images contain grey levels as a result of the anti-aliasing technique used by the normalization algorithm. the images were centered in a 28x28 image by computing the center of mass of the pixels, and translating the image so as to position this point at the center of the 28x28 field. Source: http://yann.lecun.com/exdb/mnist/ Image Source: https://en.wikipedia.org/wiki/MNIST_database#/media/File:MnistExamples.png

CoNLL-2003 is a named entity recognition dataset released as a part of CoNLL-2003 shared task: language-independent named entity recognition. The data consists of eight files covering two languages: English and German. For each of the languages there is a training file, a development file, a test file and a large file with unannotated data. The English data was taken from the Reuters Corpus. This corpus consists of Reuters news stories between August 1996 and August 1997. For the training and development set, ten days worth of data were taken from the files representing the end of August 1996. For the test set, the texts were from December 1996. The preprocessed raw data covers the month of September 1996. The text for the German data was taken from the ECI Multilingual Text Corpus. This corpus consists of texts in many languages. The portion of data that was used for this task, was extracted from the German newspaper Frankfurter Rundshau. All three of the training, development and test sets were taken from articles written in one week at the end of August 1992. The raw data were taken from the months of September to December 1992. | English data | Articles | Sentences | Tokens | LOC | MISC | ORG | PER | |-------------------|----------|-----------|---------|------|------|------|------| | Training set | 946 | 14,987 | 203,621 | 7140 | 3438 | 6321 | 6600 | | Development set | 216 | 3,466 | 51,362 | 1837 | 922 | 1341 | 1842 | | Test set | 231 | 3,684 | 46,435 | 1668 | 702 | 1661 | 1617 | Number of articles, sentences, tokens and entities (locations, miscellaneous, organizations, and persons) in English data files. | German data | Articles | Sentences | Tokens | LOC | MISC | ORG | PER | |-------------------|----------|-----------|---------|------|------|------|------| | Training set | 553 | 12,705 | 206,931 | 4363 | 2288 | 2427 | 2773 | | Development set | 201 | 3,068 | 51,444 | 1181 | 1010 | 1241 | 1401 | | Test set | 155 | 3,160 | 51,943 | 1035 | 670 | 773 | 1195 | Number of articles, sentences, tokens and entities (locations, miscellaneous, organizations, and persons) in German data files.

Simplified Chinese dataset for NER in The Third International Chinese Language Processing Bakeoff (2006), provided by Microsoft Research Asia (MSRA).

Development of a benchmark corpus to support the automatic extraction of drug-related adverse effects from medical case reports. A significant amount of information about drug-related safety issues such as adverse effects are published in medical case reports that can only be explored by human readers due to their unstructured nature. The work presented here aims at generating a systematically annotated corpus that can support the development and validation of methods for the automatic extraction of drug-related adverse effects from medical case reports. The documents are systematically double annotated in various rounds to ensure consistent annotations. The annotated documents are finally harmonized to generate representative consensus annotations. In order to demonstrate an example use case scenario, the corpus was employed to train and validate models for the classification of informative against the non-informative sentences. A Maximum Entropy classifier trained with simple features and evaluated by 10-fold cross-validation resulted in the F₁ score of 0.70 indicating a potential useful application of the corpus.

Introduced by Krallinger et al. in The CHEMDNER corpus of chemicals and drugs and its annotation principles BC4CHEMD is a collection of 10,000 PubMed abstracts that contain a total of 84,355 chemical entity mentions labeled manually by expert chemistry literature curators.

Danish Dependency Treebank (DaNE) is a named entity annotation for the Danish Universal Dependencies treebank using the CoNLL-2003 annotation scheme. Source: DaNE: A Named Entity Resource for Danish

fine-grained location names extraction from disaster-related tweets

FiNER-139 is comprised of 1.1M sentences annotated with eXtensive Business Reporting Language (XBRL) tags extracted from annual and quarterly reports of publicly-traded companies in the US. Unlike other entity extraction tasks, like named entity recognition (NER) or contract element extraction, which typically require identifying entities of a small set of common types (e.g., persons, organizations), FiNER-139 uses a much larger label set of 139 entity types. Another important difference from typical entity extraction is that FiNER focuses on numeric tokens, with the correct tag depending mostly on context, not the token itself.

The dataset used to pre-train NuNER from the NuNER: Entity Recognition Encoder Pre-training via LLM-Annotated Data Contains AI-extracted entities, their concepts, and descriptions from the given text

A growing number of papers are published in the area of superconducting materials science. However, novel text and data mining (TDM) processes are still needed to efficiently access and exploit this accumulated knowledge, paving the way towards data-driven materials design. Herein, we present SuperMat (Superconductor Materials), an annotated corpus of linked data derived from scientific publications on superconductors, which comprises 142 articles, 16052 entities, and 1398 links that are characterised into six categories: the names, classes, and properties of materials; links to their respective superconducting critical temperature (Tc); and parametric conditions such as applied pressure or measurement methods. The construction of SuperMat resulted from a fruitful collaboration between computer scientists and material scientists, and its high quality is ensured through validation by domain experts. The quality of the annotation guidelines was ensured by satisfactory Inter Annotator Agreement (IAA) between the annotators and the domain experts.

We present the development of a Named Entity Recognition (NER) dataset for Tagalog. This corpus helps fill the resource gap present in Philippine languages today, where NER resources are scarce. The texts were obtained from a pretraining corpora containing news reports, and were labeled by native speakers in an iterative fashion. The resulting dataset contains ~7.8k documents across three entity types: Person, Organization, and Location. The inter-annotator agreement, as measured by Cohen's κ, is 0.81. We also conducted extensive empirical evaluation of state-of-the-art methods across supervised and transfer learning settings. Finally, we released the data and processing code publicly to inspire future work on Tagalog NLP.

Biographical is a semi-supervised dataset for RE. The dataset, which is aimed towards digital humanities (DH) and historical research, is automatically compiled by aligning sentences from Wikipedia articles with matching structured data from sources including Pantheon and Wikidata.

This dataset was collected as part of the multidisciplinary project Femmes face aux défis de la transformation numérique : une étude de cas dans le secteur des assurances (Women Facing the Challenges of Digital Transformation: A Case Study in the Insurance Sector) at Université Laval, funded by the Future Skills Centre. It includes job offers, in French, from insurance companies between 2009 and 2020.

InLegalNER is a corpus of 46545 annotated legal named entities mapped to 14 legal entity types. It is designed for named entity recognition in indian court judgement. Source: Named Entity Recognition in Indian court judgments Image Source: https://arxiv.org/pdf/2211.03442v1.pdf

LEPISZCZE is an open-source comprehensive benchmark for Polish NLP and a continuous-submission leaderboard, concentrating public Polish datasets (existing and new) in specific tasks. Source: This is the way: designing and compiling LEPISZCZE, a comprehensive NLP benchmark for Polish Image Source: https://arxiv.org/pdf/2211.13112v1.pdf

Cybersecurity education is exceptionally challenging as it involves learning the complex attacks; tools and developing critical problem-solving skills to defend the systems. For a student or novice researcher in the cybersecurity domain, there is a need to design an adaptive learning strategy that can break complex tasks and concepts into simple representations. An AI-enabled automated cybersecurity education system can improve cognitive engagement and active learning. Knowledge graphs (KG) provide a visual representation in a graph that can reason and interpret from the underlying data, making them suitable for use in education and interactive learning. However, there are no publicly available datasets for the cybersecurity education domain to build such systems. The data is present as unstructured educational course material, Wiki pages, capture the flag (CTF) writeups, etc. Creating knowledge graphs from unstructured text is challenging without an ontology or annotated dataset. However, data annotation for cybersecurity needs domain experts. To address these gaps, we made three contributions in this paper. First, we propose an ontology for the cybersecurity education domain for students and novice learners. Second, we develop AISecKG, a triple dataset with cybersecurity-related entities and relations as defined by the ontology. This dataset can be used to construct knowledge graphs to teach cybersecurity and promote cognitive learning. It can also be used to build downstream applications like recommendation systems or self-learning question-answering systems for students. The dataset would also help identify malicious named entities and their probable impact. Third, using this dataset, we show a downstream application to extract custom-named entities from texts and educational material on cybersecurity.

HAREM, an initiative by Linguateca, boasts a Golden Collection—a meticulously curated repository of annotated Portuguese texts. This resource serves as a pivotal benchmark for evaluating systems in recognizing mentioned entities within documents. It stands as a cornerstone, supporting advancements and innovations in Portuguese language processing research, providing a comprehensive foundation for evaluating system performances and fostering ongoing developments in this domain.

The dataset is taken from the First shared task on Information Extractor for Conversational Systems in Indian Languages (IECSIL) . It consists of 15,48,570 Hindi words in Devanagari script and corresponding NER labels. Each sentence end is marked by \newline" tag. Fig. 1 shows a snapshot of one sentence in the dataset. Our Dataset has nine classes, namely, Datenum, Event, Location, Name, Number, Occupation, Organization, Other, Things. Image taken from paper: https://www.researchgate.net/publication/349190662_Analysis_of_Contextual_and_Non-contextual_Word_Embedding_Models_for_Hindi_NER_with_Web_Application_for_Data_Collection

The MiniHAREM, a reiteration of the 2005 evaluation, used the same methodology and platform. Held from April 3rd to 5th, 2006, it offered participants a 48-hour window to annotate, verify, and submit text collections. Results are available, and the collection used is accessible. Participant lists, submitted outputs, and updated guidelines are provided. Additionally, the HAREM format checker ensures compliance with MiniHAREM directives. Information for the HAREM Meeting, open for registration until June 15th after the Linguateca Summer School in the University of Porto, is also available.

RaTE-NER dataset is a large-scale, radiological named entity recognition (NER) dataset, including 13,235 manually annotated sentences from 1,816 reports within the MIMIC-IV database, that spans 9 imaging modalities and 23 anatomical regions, ensuring comprehensive coverage. Additionally, we further enriched the dataset with 33,605 sentences from the 17,432 reports available on Radiopaedia, by leveraging GPT-4 and other medical knowledge libraries to capture intricacies and nuances of less common diseases and abnormalities. We manually labeled 3,529 sentences to create a test set.

TASTEset Recipe Dataset and Food Entities Recognition is a dataset for Named Entity Recognition (NER) which consists of 700 recipes with more than 13,000 entities to extract.

We present the SourceData-NLP dataset produced through the routine curation of papers during the publication process. A unique feature of this dataset is its emphasis on the annotation of bioentities in figure legends. We annotate eight classes of biomedical entities (small molecules, gene products, subcellular components, cell lines, cell types, tissues, organisms, and diseases), their role in the experimental design, and the nature of the experimental method as an additional class. SourceData-NLP contains more than 620,000 annotated biomedical entities, curated from 18,689 figures in 3,223 papers in molecular and cell biology. We illustrate the dataset's usefulness by assessing BioLinkBERT and PubmedBERT, two transformers-based models, fine-tuned on the SourceData-NLP dataset for NER. We also introduce a novel context-dependent semantic task that infers whether an entity is the target of a controlled intervention or the object of measurement.

Based on RADDLE and SNIPS , we construct Noise-SF, which includes two different perturbation settings. For single perturbations setting, we include five types of noisy utterances (character-level: \textbf{Typos}, word-level: \textbf{Speech}, and sentence-level: \textbf{Simplification}, \textbf{Verbose}, and \textbf{Paraphrase}) from RADDLE. For mixed perturbations setting, we utilize TextFlint to introduce character-level perturbation (\textbf{EntTypos}), word-level perturbation (\textbf{Subword}), and sentence-level perturbation (\textbf{AppendIrr}) and combine them to get a mixed perturbations dataset.

POPCORN is a French dataset consisting of 400 validation texts and 400 training texts, all written and annotated manually. The texts are concise and factual, resembling information reports. The annotations, based on the ontology described below, allow for the training and evaluation of models in Information Extraction tasks, including Named Entity Recognition, Coreference Resolution, and Relation Extraction. Additionally, 400 more texts have been provided for the TextMine 2025 challenge on Relation Extraction, which can be accessed via the following link: https://www.kaggle.com/competitions/defi-text-mine-2025/

The Second HAREM was an evaluation exercise in Portuguese Named Entity Recognition. It aims to refine text annotation processes, building on the First HAREM. Challenges include adapting guidelines for new texts and establishing a unified document with directives from both editions.

This dataset was taken from the SIGARRA information system at the University of Porto (UP). Every organic unit has its own domain and produces academic news. We collected a sample of 1000 news, manually annotating 905 using the Brat rapid annotation tool. This dataset consists of three files. The first is a CSV file containing news published between 2016-12-14 and 2017-03-01. The second file is a ZIP archive containing one directory per organic unit, with a text file and an annotations file per news article. The third file is an XML containing the complete set of news in a similar format to the HAREM dataset format. This dataset is particularly adequate for training named entity recognition models.

Introduction: The scientific publishing landscape is expanding rapidly, creating challenges for researchers to stay up-to-date with the evolution of the literature. Natural Language Processing (NLP) has emerged as a potent approach to automating knowledge extraction from this vast amount of publications and preprints. Tasks such as Named-Entity Recognition (NER) and Named-Entity Linking (NEL), in conjunction with context-dependent semantic interpretation, offer promising and complementary approaches to extracting structured information and revealing key concepts. Results: We present the SourceData-NLP dataset produced through the routine curation of papers during the publication process. A unique feature of this dataset is its emphasis on the annotation of bioentities in figure legends. We annotate eight classes of biomedical entities (small molecules, gene products, subcellular components, cell lines, cell types, tissues, organisms, and diseases), their role in the experimental design, and the nature of the experimental method as an additional class. SourceData-NLP contains more than 620,000 annotated biomedical entities, curated from 18,689 figures in 3,223 papers in molecular and cell biology. We illustrate the dataset's usefulness by assessing BioLinkBERT and PubmedBERT, two transformers-based models, fine-tuned on the SourceData-NLP dataset for NER. We also introduce a novel context-dependent semantic task that infers whether an entity is the target of a controlled intervention or the object of measurement. Conclusions: SourceData-NLP's scale highlights the value of integrating curation into publishing. Models trained with SourceData-NLP will furthermore enable the development of tools able to extract causal hypotheses from the literature and assemble them into knowledge graphs.