tttthomasssss

wort

Am Anfang war das Wort.

iwcs2019

Resources from our IWCS 2019 paper: Temporal and Aspectual Entailment

acl2017

Code and resources of the ACL 2017 paper "Improving Semantic Composition with Offset Inference"

apt-toolkit

Toolkit for working with APTs

PyHugeThesaurusConnector

sense2017

Code and Task setup of the paper "One Representation per Word - Does it make Sense for Composition?"

coling2020

Aspectuality across Genre: A Distributional Semantics Approach

clustering

some cluster utils

le-augmentation

Data Augmentation for Lexical Inference

transformers

🤗 Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.

whatlies

toolkit to help visualise - what lies in word embeddings

wolkenatlas

All your embeddings are belong to us

conf2017slides

DiscoUtils

dissect-py3

python3 port of `dissect` (https://github.com/composes-toolkit/dissect)

dotfiles

dotfiles

EvaluationMethods

meetups

PyData Edinburgh Monthly Meetup Materials

moab

mother of all bibs

paralysis

Parameter analysis and feature ablation by fitting a linear model

rasa

💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants

repeval2016

A critique of word similarity as a method for evaluating distributional semantic models

reversibledict

A quick & simple (and probably dirty) implementation of a dictionary capable of performing a reverse lookup.

sacred

Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.

scikit-learn

scikit-learn: machine learning in Python

scipy

Scipy library main repository

skip-thoughts

Sent2Vec encoder and training code from the paper "Skip-Thought Vectors"

tttthomasssss.github.io

tttthomasssss.github.io-src

ubuntu-ranking-dataset-creator

A script that creates train, valid and test datasets for the ranking task from Ubuntu corpus dialogs.