STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases (https://stark.stanford.edu/)
-
Updated
Jun 25, 2024 - Python
STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases (https://stark.stanford.edu/)
Implementation of the semi-structured inference model in our ACL 2020 paper, INFOTABS: Inference on Tables as Semi-structured Data.
Programming language for symbolic computation with unusual combination of pattern matching features: Tree patterns, associative patterns and expressions embedded in patterns.
Refinery is a tool to extract and transform semi-structured data from Excel spreadsheets of different layouts in a declarative way.
Repository containing code for the NAACL 2021 paper (Incorporating External Knowledge to Enhance Tabular Reasoning)
Endoscopic and Pathological data extraction for various endo-pathological data extraction
A dataset for extracting information from repair manuals
A semi-automatic web-based annotation tool for MyFixit dataset :
Web-based workflow management system that computes candidate tool workflows given input file(s) and the user's requirements regarding the output. Afterwards, runs a workflow selected by the user from the list of candidates. Implemented in Bracmat (~75%) and Java (~25%).
This repository contains the official code for the paper : Realistic Data Augmentation Framework for Enhancing Tabular Reasoning.
Framework to manipulate semi structured documents and extract data from them
Endoscopic and Pathological data extraction for various endo-pathological data extraction
Documentation how you can use the Any2Json to load documents from "real life".
Report of a project concerning database construction, management and manipulation that uses various .xml and .csv files from open sources with semi-structured and unstructured data. The analysis is visualised by RShiny dashboard.
Any2Json Net Classifier Plugin
Repository of basic Models for Any2Json
Any2Jaon Parquet Plugin
Add a description, image, and links to the semi-structured-data topic page so that developers can more easily learn about it.
To associate your repository with the semi-structured-data topic, visit your repo's landing page and select "manage topics."