• Research softwareclose
• 2022-2022close
• Digital Humanities and Cultural Heritage close
• Knowmad Institut close

This repository is created for sharing materials (e.g., sample data, trained models, and demo files) for our work. The demo files in the repository allow users to run our models on their own data or on sample data that we provide. The repository includes the following four components: A code demonstration of review text preprocessing. (ReviewPreprocess.zip) The lexicon and a code demonstration of using the lexicon to generate input for the two lexicon-based classification models. (LexiconModels.zip) The trained Doc2Vec model and a code demonstration of obtaining Doc2Vec embeddings using this model. (Doc2VecEmbeddings.zip) Trained base-learner classification models (M2, M3, M4), optimized weights for the ensemble model E2, and the trained ensemble model (E3). We also provide a code demonstration of classifying reviews using our proposed models. (ClassificationModels.zip) The data used for building these models can be requested from the Global Emancipation Network for approved uses established in a data use agreement. This work was funded by the National Science Foundation under award #1936331.

When using ASReview LAB to screen titles and abstracts in a systematic review, wordclouds can visualize the words that are used the most within the titles and/or abstracts. The package also allows to create wordclouds for the relevant inclusions only.

ASReview Datatools is an extension to ASReview LAB that can be used for describing basic properties of a dataset (e.g., number of papers, number of inclusions, the amount of missing data and duplicates), converting file formats via the command line, and cleaning your (input) data by removing duplicate records.

ASReview Insights is an extension to ASReview LAB that extends the software with tools for plotting and extracting the statistical results of several performance metrics. The extension is especially useful in combination with the simulation functionality of ASReview LAB.

The Active learning for Systematic Reviews (ASReview) project implements learning algorithms that interactively query the researcher. This way of interactive training is known as Active Learning. ASReview offers support for classical learning algorithms and state-of-the-art learning algorithms like neural networks. ASReview LAB is the graphical user interface of the open-source research software and ships with an Oracle, Exploration, and Simulation Mode. If you use this software, please cite the software and Van de Schoot et al. (2021). https://doi.org/10.1038/s42256-020-00287-7

BioVAE is a pre-trained latent variable language model for biomedical text mining. Large scale pre-trained language models (PLMs) have advanced state-of-the-art (SOTA) performance on various biomedical text mining tasks. The power of such PLMs can be combined with the advantages of deep generative models. These are examples of these combinations. However, they are trained only on general domain text, and biomedical models are still missing. In this work, we describe BioVAE, the first large scale pre-trained latent variable language model for the biomedical domain, which uses the OPTIMUS framework to train on large volumes of biomedical text. The model shows SOTA performance on several biomedical text mining tasks when compared to existing publicly available biomedical PLMs.

BERT-Kcr is a tool for prediction of lysine crotonylation sites by a transfer learning method with pre-trained BERT models.

ProtTrans is providing state of the art pre-trained models for proteins. ProtTrans was trained on thousands of GPUs from Summit and hundreds of Google TPUs using various Transformers Models.

A hybrid embedding-based text representation for HMTC