Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
12
datasets available to search
ShareScore release 0.9.0
Dataset results
12 results for “Paraphrase”
Identifying Machine-Paraphrased Plagiarism
<p>README.txt</p> <p>Title: <em>Identifying Machine-Paraphrased Plagiarism</em><br> Authors: Jan Philip Wahle, Terry Ruas, Tomas Foltynek, Norman Meuschke, and Bela Gipp<br> contact email: wahle@gipplab.org; ruas@gipplab.org;<br> Venue: iConference<br> Year: 2022<br> ================================================================<br> <strong>Dataset Description:</strong></p> <p><em><strong>Training:</strong></em><br> 200,767 paragraphs (98,282 original, 102,485paraphrased) extracted from 8,024 Wikipedia (English) articles (4,012 original, 4,012 paraphrased using the SpinBot API).</p> <p><em><strong>Testing:</strong></em><br> SpinBot: <br> arXiv - Original - 20,966; Spun - 20,867<br> Theses - Original - 5,226; Spun - 3,463<br> Wikipedia - Original - 39,241; Spun - 40,729<br> <br> SpinnerChief-4W: <br> arXiv - Original - 20,966; Spun - 21,671<br> Theses - Original - 2,379; Spun - 2,941<br> Wikipedia - Original - 39,241; Spun - 39,618<br> <br> SpinnerChief-2W: <br> arXiv - Original - 20,966; Spun - 21,719<br> Theses - Original - 2,379; Spun - 2,941<br> Wikipedia - Original - 39,241; Spun - 39,697</p> <p>================================================================<br> Dataset Structure:</p> <p><strong>[human_evaluation]</strong> folder: human evaluation to identify human-generated text and machine-paraphrased text. It contains the files (original and spun) as for the answer-key for the survey performed with human subjects (all data is anonymous for privacy reasons).</p> <p>NNNNN.txt - whole document from which an extract was taken for human evaluation<br> key.txt.zip - information about each case (ORIG/SPUN)<br> results.xlsx - raw results downloaded from the survey tool (the extracts which humans judged are in the first line)<br> results-corrected.xlsx - at the very beginning, there was a mistake in one question (wrong extract). These results were excluded.</p> <p><br> <strong>[automated_evaluation]: </strong>contains all files used for the automated evaluation considering [spinbot] (https://spinbot.com/API) and [spinnerchief] (http://developer.spinnerchief.com/API_Document.aspx).</p> <ul> <li>Each paraphrase tool folder contains:</li> <li><strong>[corpus] </strong>and<strong> [vectors]</strong> sub-folders.</li> <li>For [spinnerchief], two variations are included, with 4-word-chaging ratio (default) and 2-word-chaging ratio. </li> </ul> <p><strong>[vectors] sub-folder</strong> contains the average of all word vectors for each paragraph. Each line has the number of dimensions of the word embeddings technique used (see paper for more details) followed by its respective class (i.e., label mg or og). Each file belongs to one class, either "mg" or "og". The values are comma-separated (.csv). The extension is .arff can be read as a normal .txt file.</p> <ul> <li>The word embedding technique used is described in the file name with the following structure: <technique>-<type>-mean-<data>.arff . Where</li> </ul> <p><em><technique></em> - d2v - doc2vec<br> google - word2vec<br> fasttextnw - fastText without subwording<br> fasttextsw - fastText with subwording<br> glove - Glove<br> <br> Details for each technique used can be found in the paper.<br> <br> <em><type> - </em> arxivp - arXiv paragraph split<br> thesisp - Theses paragraph split<br> wikip - Wikipedia paragraph split (wikipedia_paragraph_vector_train are the vectors used for training. It follows the same wikip structure) </p> <p>Details for each technique used can be found in the paper referenced at the start of this README file.</p> <p><strong>[corpus] sub-folder:</strong> contains de raw text (No pre-processing) used for train and test at a paragraph level.</p> <ul> <li>The Spun paragraphs used for <strong>training</strong> are only generated using the <strong>SpinBot tool</strong>. For test both SpinBot and SpinnerChief are used. </li> <li>The paragraph split is generated by selecting paragraphs from the original documents with 3 or more sentences. Each folder is divided in mg (i.e., machine-generated through SpinBot and SpinnerChief) and og (i.e., original-generated file). the document split is not avaiable since our experiments only use the paragraph level.</li> <li>Machine Learning models: SVM, Naive Bayes, and Logistic Regression. The grid search for hyperparameter adjustments for the machine learning classifiers is described in the paper.</li> </ul> <p>@incollection{WahleRFM22,<br> title = {Identifying {{Machine-Paraphrased Plagiarism}}},<br> booktitle = {Information for a {{Better World}}: {{Shaping}} the {{Global Future}}},<br> author = {Wahle, Jan Philip and Ruas, Terry and Folt{\’y}nek, Tom{\’a}{\v s} and Meuschke, Norman and Gipp, Bela},<br> editor = {Smits, Malte},<br> year = {2022},<br> volume = {13192},<br> pages = {393--413},<br> publisher = {{Springer International Publishing}},<br> address = {{Cham}},<br> doi = {10.1007/978-3-030-96957-8_34},<br> isbn = {978-3-030-96956-1 978-3-030-96957-8},<br> }</p> <p> </p> <p>For our previous publication using only SpinBot and Wikipedia articles for document and paragraph split, please see the following publication. The dataset used is hosted in <a href="https://deepblue.lib.umich.edu/data/concern/data_sets/2801pg45f?locale=en">DeepBlue</a></p> <p><br> </p>
German Compounds and Paraphrases
<p>++++ english below ++++</p> <p>Beschreibung der enthaltenen Datensätze:</p> <p><br> all-phrases.csv:</p> <p>Was beinhalten die Spalten?</p> <p>| Kompositum | Erstes Kompositionsglied | Zweites Kompositionsglied | Frequenz des Kompositums im Korpus* | Paraphrasierung | Frequenz der Paraphrasierung im Korpus* |</p> <p>*Der Korpus, welcher für Extraktion der Phrasen und beider Frequenzwerte verwendet wurde, zu finden unter: https://corpora.uni-leipzig.de/de?corpusId=deu_newscrawl_2011</p> <p><br> labeled-phrases.csv:</p> <p>Hat den gleichen Aufbau wie all-phrases.csv mit einer zusatzlichen Spalte:</p> <p>|...| Label |</p> <p>Das Label hat die Werte 0 oder 1. Es ist eine Bewertung der zugehörigen Paraphrasierung, wobei 1 für 'richtig' und 1 für 'falsch' steht.</p> <p> </p> <p>++++ english ++++</p> <p>discription of datasets:</p> <p><br> all-phrases.csv:</p> <p>What do the columns contain?</p> <p>| compound word | first element of compound | second element of compound | frequency of compound in corpus* | phrase | frequency of phrase in corpus* |</p> <p>*Meaning the corpus used to obtain the phrases and both frequencies. Can be found here: https://corpora.uni-leipzig.de/de?corpusId=deu_newscrawl_2011</p> <p><br> labeled-phrases.csv:</p> <p>this one has the same columns as the previous dataset with one addition:</p> <p>|...| label |</p> <p>the labes has values of either 0 or 1. It is an evaluation of the correctness of the phrase with 1 meaning 'correct' and 0 meaning 'false'. </p>
Webis Crowd Paraphrase Corpus 2011 (Webis-CPC-11)
<p>The Webis Crowd Paraphrase Corpus 2011 (Webis-CPC-11) contains 7,859 candidate paraphrases obtained from Mechanical Turk crowdsourcing. The corpus is made up of 4,067 accepted paraphrases, 3,792 rejected non-paraphrases, and the original texts. These samples have formed part of <a href="https://doi.org/10.5281/zenodo.3250123">PAN 2010</a> international plagiarism detection competition, but were not previously available separate to rest of the competition data.</p> <p>We provide the dataset as a single folder in a Zip archive. Each paraphrase is represented by three files, containing the original text (e.g.: "1-original.txt"), the paraphrase text (e.g.: "1-paraphrase.txt"), and a file containing metadata (e.g.: "1-metadata.txt"), with information about the task identifier, task author identifier, time taken, and whether the paraphrase was accepted or rejected.</p>
Transfer fine-tuned BERT models by paraphrases
<p>Transfer fine-tuned BERT models by phrasal paraphrases. </p> <ul> <li>transferFT_bert-base-uncased.pkl bases on the bert-base-uncased model</li> <li>transferFT_bert-large-uncased.pkl bases on the bert-large-uncased model</li> </ul> <p>For usage, please refer to our GitHub page.</p> <p><a href="https://github.com/yukiar/TransferFT">https://github.com/yukiar/TransferFT</a></p> <p>For details of these models, please refer to our paper.</p> <p>Yuki Arase and Junichi Tsujii. 2019. Transfer Fine-Tuning: A BERT Case Study. in Proc. of Conference on Empirical Methods in Natural Language Processing (EMNLP 2019).</p> <p><a href="https://arxiv.org/abs/1909.00931">https://arxiv.org/abs/1909.00931</a></p>
TaPaCo: A Corpus of Sentential Paraphrases for 73 Languages
<p>This paper presents TaPaCo, a freely available paraphrase corpus for 73 languages extracted from the Tatoeba database. Tatoeba is a crowdsourcing project mainly geared towards language learners. Its aim is to provide example sentences and translations for particular linguistic constructions and words. The paraphrase corpus is created by populating a graph with Tatoeba sentences and equivalence links between sentences "meaning the same thing". This graph is then traversed to extract sets of paraphrases. Several language-independent filters and pruning steps are applied to remove uninteresting sentences. A manual evaluation performed on three languages shows that between half and three quarters of inferred paraphrases are correct and that most remaining ones are either correct but trivial, or near-paraphrases that neutralize a morphological distinction. The corpus contains a total of 1.9 million sentences, with 200 - 250 000 sentences per language. It covers a range of languages for which, to our knowledge, no other paraphrase dataset exists.</p>
XSum and CNN with paraphrases of summaries
<p>These datasets contain the original datasets and paraphrases of the summaries.</p><p>CNN/DailyMail is available at https://huggingface.co/datasets/cnn_dailymail released under the Apache 2.0 license. </p><p>XSum is available at https://huggingface.co/datasets/EdinburghNLP/xsum and was originally released under the MIT license.</p><p>The paraphraser is https://huggingface.co/humarin/chatgpt_paraphraser_on_T5_base available under the OpenRAIL license.</p>
IO Islamic 1762. Tarjuma-i-Ta'rîkh-alḥukamâ, A Persian Paraphrase of Maulânâ Shams-aldîn Muḥammad Suhrawardî's Biographies of Ancient Philosophers and Wise Men
<p>IO Islamic 1762. Tarjuma-i-Ta’rîkh-alḥukamâ, A Persian Paraphrase of Maulânâ Shams-aldîn Muḥammad Suhrawardî’s Biographies of Ancient Philosophers and Wise Men</p>
Task-Oriented Paraphrase Analytics
<p>Data accompanying the paper <em>"Task-Oriented Paraphrase Analytics"</em> at LREC-COLING 2024.</p>
IO Islamic 2380. Rauḍat-alshuhadâ,Paraphrase in Dakhnî verses
<p>IO Islamic 2380. Rauḍat-alshuhadâ,Paraphrase in Dakhnî verses</p>
IO Islamic 1579. Tarjuma-i-Ta'rîkh-alḥukamâ, A Persian Paraphrase of Maulânâ Shams-aldîn Muḥammad Suhrawardî's Biographies of Ancient Philosophers and Wise Men
<p>IO Islamic 1579. Tarjuma-i-Ta’rîkh-alḥukamâ, A Persian Paraphrase of Maulânâ Shams-aldîn Muḥammad Suhrawardî’s Biographies of Ancient Philosophers and Wise Men</p>
IO Islamic 1423. Tarjuma-i-Ta'rîkh-alḥukamâ, A Persian Paraphrase of Maulânâ Shams-aldîn Muḥammad Suhrawardî's Biographies of Ancient Philosophers and Wise Men
<p>IO Islamic 1423. Tarjuma-i-Ta’rîkh-alḥukamâ, A Persian Paraphrase of Maulânâ Shams-aldîn Muḥammad Suhrawardî’s Biographies of Ancient Philosophers and Wise Men</p>
IO Islamic 063. Tarjuma-i-Ta'rîkh-alḥukamâ, A Persian Paraphrase of Maulânâ Shams-aldîn Muḥammad Suhrawardî's Biographies of Ancient Philosophers and Wise Men
<p>IO Islamic 063. Tarjuma-i-Ta’rîkh-alḥukamâ, A Persian Paraphrase of Maulânâ Shams-aldîn Muḥammad Suhrawardî’s Biographies of Ancient Philosophers and Wise Men</p>
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.