Compare Skimle vs. TILDE

Skimle revolutionizes the way unstructured qualitative data is converted into structured, analyzable datasets through the use of artificial intelligence. In contrast to RAG chatbots that simply retrieve isolated excerpts, Skimle meticulously processes complete sets of documents from the outset—examining each segment, gathering insights, and categorizing them within a structured hierarchy of themes. You can upload various formats of qualitative data such as interview transcripts, PDFs, audio or video files, and reports. The workflow that Skimle employs, which draws inspiration from scholarly thematic analysis, systematically codes every passage, uncovers recurring patterns, and compiles a comprehensive "spreadsheet" where documents are organized as rows and themes as columns. Each insight is directly tied to verified quotes, ensuring accuracy without any fabrication. Supporting over 100 languages and capable of handling more than 1,000 documents per project, Skimle is fully compliant with GDPR regulations applicable in the EU, providing complete traceability between themes and quotes. Users can also enjoy features such as customizable categories, AI-driven chat for reasoning, and options to export findings into Word, Excel, or PowerPoint formats. What sets Skimle apart is its ability to merge the rigorous standards of academic research with the rapid processing capabilities of AI. Tasks that traditionally consume weeks when using NVivo or other conventional tools can be completed in mere hours with Skimle, all while maintaining detailed audit trails essential for peer review and validation. This efficiency not only saves time but enhances the overall research experience, making qualitative analysis more accessible and streamlined than ever before.

TILDE (Term Independent Likelihood moDEl) serves as a framework for passage re-ranking and expansion, utilizing BERT to boost retrieval effectiveness by merging sparse term matching with advanced contextual representations. The initial version of TILDE calculates term weights across the full BERT vocabulary, which can result in significantly large index sizes. To optimize this, TILDEv2 offers a more streamlined method by determining term weights solely for words found in expanded passages, leading to indexes that are 99% smaller compared to those generated by the original TILDE. This increased efficiency is made possible by employing TILDE as a model for passage expansion, where passages are augmented with top-k terms (such as the top 200) to enhance their overall content. Additionally, it includes scripts that facilitate the indexing of collections, the re-ranking of BM25 results, and the training of models on datasets like MS MARCO, thereby providing a comprehensive toolkit for improving information retrieval tasks. Ultimately, TILDEv2 represents a significant advancement in managing and optimizing passage retrieval systems.