mir-mu Goto Github PK

arqmath-data-preprocessing

Preprocessed ARQMath competition datasets

arqmath-eval

Evaluation of systems for the ARQMath competition

arqmathcode

coat

Implementation of Concept-aware Training for efficient training of in-context learners

compubert

Adaptation of Transformers architecture to resolve ARQMath CLEF 2020 Competition: Answer Retrieval and Formula Search

document-maps

A visual text information retrieval system

document-maps-visualization

A visual text information retrieval system

fasttext-optimizer

Suggests subword sizes for fastText language models using character n-gram frequency analysis.

faust

Narrative search engine for edustories.cz, open for everyone

ffmpeg-tensorflow

Dockerfile for FFMpeg with Libtensorflow

isbiased

A library to measure biases of question answering models.

mathmlcan

Canonicalizes different MathML encodings of equivalent formulae

mathmlcaneval

Provides a web application for the evaluation of the MathML Canonicalizer

mathmlunificator

Generalizes distinct mathematical formulae so that they can be structurally unified

mias

Indexes text with math in Lucene/Solr-based full-text search engines

miasmath

Adds math processing capabilities to Lucene or Solr

mireval

Evaluates search results produced by the NTCIR MIaS Search package

ntcir-math-density

Uses datasets, and judgements in the NTCIR-11 Math-2, and NTCIR-12 MathIR XHTML5 format to compute density, and probability estimators

ntcir-mias-deployment

Deploys WebMIaS, MIREval, and NTCIR MIaS Search to reproduce NTCIR-11 Math-2 main task results

ntcir-mias-search

Implements the Math Information Retrieval system that won the NTCIR-11 Math-2 main task (Růžička et al., 2014)

ntcir10-math-converter

Converts NTCIR-10 Math XHTML5 dataset and relevance judgements to the NTCIR-11 Math-2, and NTCIR-12 MathIR XHTML5 format

pine

A python package that allows you to train, use, and evaluate position-independent word embeddings (PInE).

pv211-utils

Utilities for the term project in the PV211 introduction to information retrieval course

regemt

Regressive ensemble for machine translation evaluation

regularized-embeddings

Experimental code for the “Text classification with word embedding regularization and soft similarity measure” (Novotný et al., 2020) paper

reproducible-ml

Experimental code for the paper “The Art of Reproducible Machine Learning: A Survey of Methodology in Word Vector Experiments”

scm-at-arqmath

The math information retrieval (MIR) system for the ARQMath competition based on the tf-idf model and the soft cosine measure

seqrep

Scientific framework for representation in sequential data

softalign_objectives

Implementation of ACL 2023's paper: Soft Alignment Objectives for Robust Adaptation of Language Generation

sr

Image and video super resolution