Applica's Projects
Index of URLs to pdf files all over the internet and scripts
Data and additional information regarding the paper: Contract Discovery. Dataset and a Few-Shot Semantic Retrieval Challenge with Competitive Baselines (to appear in Findings of EMNLP).
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
Publicly released code for the LAMBERT model
The repository contains model implementations and data described in the paper: From Dataset Recycling to Multi-Property Extraction and Beyond.
Additional datasets for Named Entity Recognition
Natural language processing webservice for polish language
Playing with training and testing sets: active learning, interpretability and black-box machine learning debugging
Code and data accompanying the paper "Approaching nested named entity recognition with parallel LSTM-CRFs."
This repository contains a demonstrative implementation for pooling-based models, e.g., DeepPyramidion complementing our paper "Sparsifying Transformer Models with Trainable Representation Pooling."
The driver making it convenient to use Temporal with Spring Boot.
A fast and highly accurate differentiable Top-k operator from the "Successive Halving Top-k Operator" AAAI'21 paper.
Fork of https://github.com/MI2DataLab/WildNLP with changes done by Kamil Grabowski for a MsC Thesis. Go to the original repository for more information.