gkaramanolakis Goto Github PK

academic-website

adsm

Audio-based Distributional Semantic Models (ADSM) toolkit

anchor

Code for "High-Precision Model-Agnostic Explanations" paper

anchor-topic

This package supports implementation of anchor-based topic modeling and variants of the anchoring algorithm in Python 3.

astra

Self-training with Weak Supervision (NAACL 2021)

bangladesh-nlp-flood-research

Bangladesh NLP Flood Research

bokeh

Interactive Web Plotting for Python

clts

Cross-lingual Transfer of Weak Supervision (EMNLP Findings 2020)

disclda

Supervised Topic modeling with Discriminative Latent Dirichlet Allocation using Collapsed Gibbs sampling

ekphrasis

Collection of lightweight text processing tools, geared towards text from social networks, such as Twitter or Facebook. Ekphrasis performs tokenization, word normalization, word segmentation (for splitting hashtags) and spell correction, using word statistics from 2 big corpora (english Wikipedia, twitter - 330mil english tweets).

fasttext

Library for fast text representation and classification.

foodborneml

foodbornenyc

Discovering foodborne illness outbreaks on Yelp and Twitter for the NYC DOHMH

git-class

A 4h class to teach git and GitHub

gkaramanolakis.github.io

Portfolio website

hierarchical-attention-networks

Document classification with Hierarchical Attention Networks in TensorFlow

iswd

Iterative Seed Word Distillation (EMNLP 2019)

librosa

Python library for audio and music analysis

lightning

Data Visualization Server

lime

Lime: Explaining the predictions of any machine learning classifier

magenta

Magenta: Music and Art Generation with Machine Intelligence

mmfeat

Multi-modal features toolkit in Python

models

Models built with TensorFlow

natural-instructions-expansion

Expanding natural instructions

pydub

Manipulate audio with a simple and easy high level interface

requests-for-research

A living collection of deep learning problems

sed_eval

Evaluation toolbox for Sound Event Detection

sentiment-discovery

Unsupervised Language Modeling at scale for robust sentiment classification

simpletransformers

Transformers made simple with training, evaluation, and prediction possible with one line each. Currently supports Sequence Classification (binary, multiclass, multilabel, sentence pair), Token Classification (NER), Question Answering, and Regression tasks. Built on top of the Hugging Face Transformer library.

spacyspanbert

Using spaCy & SpanBERT for relation extraction from web documents.