• ML adaptation for RNN and LLM models in AI Factory 2.0

    ML adaptation for RNN and LLM models in AI Factory 2.0

    The AI Factory no-code Machine Learning dashboard offers training capabilities for Classification and Named Entity Recognition. Each option relies on different algorithms: The reason why you would use either the RNN Classifier or the Transformers-based (XT) Classifier has much to do with the amount of training data you have and […]

  • Throughput benchmark: AI Factory engines provide unprecedented speed on commodity hardware

    Throughput benchmark: AI Factory engines provide unprecedented speed on commodity hardware

    One of the key differentiators of AI Factory‘s Text Analytics capabilities is the ability to process content at tremendous speeds even on commodity hardware. With the AI Factory version 2.0 release his capability was enhanced across the entire machine learning to inference pipeline, with hardware optimization taking place for all […]

  • Multi-class vs. Multi-label Classification

    Multi-class vs. Multi-label Classification

    The most common AI Text Analytics task is Classification. Document classification works for a plethora of use- cases, from sentiment/emotion analysis, intent detection, news categorization, email classification, and so on. There are few business-related processes that do not require a classifier in order to be automated, and there are so […]

  • It’s AutoMagical! How does the AI Factory hyperparameter optimization work

    It’s AutoMagical! How does the AI Factory hyperparameter optimization work

    A new and exciting feature was added to the AI Factory version 2.0 release: The AutoMagical Settings switch for the Classifier trainers. With just a click, Factory will automatically (and magically!) determine the best hyperparameters for the training process to obtain the best AI classifier from your data. Read the […]

  • Clickbait Detection

    Clickbait Detection

    The Clickbait detection engine determines the likelyhood of a news article to be written in a “clickbait” style: designed to attract attention and to entice users to follow that link and read, view, or listen to the linked piece of online content, being typically deceptive, sensationalized, or otherwise misleading. The […]

  • Speech Transcription

    Speech Transcription

    Automated Speech Transcription automatically processes real-time or recorded audio streams into editable text. Supported languages: Romanian, 50 other languages supported, including cross-language content: Afrikaans (afr), Arabic (ara), Chinese (zho), Croatian (hrv), Czech (ces), Danish (dan), Dutch (nld), English (eng), Estonian (est), Finnish (fin), French (fra), Welsh (glg), German (deu), Greek […]

  • Automated Translation

    Automated Translation

    Automatically Translate text and documents from one language to another, with automatic identification of the source language. Supported target languages: afr (Afrikaans), amh (Amharic), ara (Arabic), ast (Asturian), aze (Azerbaijani), bak (Bashkir), bel (Belarusian), bul (Bulgarian), ben (Bengali), bre (Breton), bos (Bosnian), cat (Catalan), ceb (Cebuano), ces (Czech), cym (Welsh), […]

  • Optical Character Recognition

    Optical Character Recognition

    Transcribes text out of a given image, scan (.jpg, .png, .tif) or PDF file using a text recognition model (Computer Vision) with various settings for layout extraction: parse text, tabular, rotated, single line, uniform, and more. Supported Languages Afrikaans, Arabic, Azerbaijani, Belarusian, Bosnian, Bulgarian, Catalan, Croatian, Czech, Danish, Dutch, English, […]

  • Semantic Comparison

    Semantic Comparison

    The Semantic Similarity Engine finds identical meaning contained by the analyzed content pieces, ignoring syntax or grammar. You can even compare content pieces written in different languages. It can be used for clustering documents based on the information they contain. There are two flavors of the Semantic Similarity engine: one […]

  • Automatic Summarization

    Automatic Summarization

    Understands the meaning of a text by reading only the key sentences.  This version uses TF and TF-IDF (term frequency–inverse document frequency) numerical statistics that show how important a word or a combination of words is for a document. Using this approach, each and every sentence and phrase of a […]