Sebastian Gehrmann
sebastianGehrmann
Head of NLP in the CTO office at Bloomberg. Formerly researcher at Google.
Languages
Repos
35
Stars
362
Forks
112
Top Language
Python
Loading contributions...
Top Repositories
Code for the paper "Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias"
This repository contains data and code for the paper"Comparing deep learning and concept extraction based methods for patient phenotyping".
This repository provides scripts to train an LSTM and then extract states from it in Tensorflow.
A scraper that downloads search results from DBLP.
Repositories
35Code for the paper "Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias"
No description provided.
Personal Website
Config files for my GitHub profile.
No description provided.
This repository provides scripts to train an LSTM and then extract states from it in Tensorflow.
Continuous-time Markov model with discrete observations
A scraper that downloads search results from DBLP.
This repository contains data and code for the paper"Comparing deep learning and concept extraction based methods for patient phenotyping".
Open-Source Neural Machine Translation in PyTorch http://opennmt.net/
Beyond the Imitation Game collaborative benchmark for enormous language models
summarization baselines and their ROUGE scores
Code for AAAI 2019 paper on Data-to-Text Generation with Content Selection and Planning
🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.
🤗 Fast, efficient, open-access datasets and evaluation metrics in PyTorch, TensorFlow, NumPy and Pandas
Unsupervised text tokenizer for Neural Network-based text generation.
No description provided.
Remove problematic gender bias from word embeddings.
An open-source NLP research library, built on PyTorch.
Data loaders and abstractions for text and NLP
Sequence-to-sequence model with LSTM encoder/decoders and attention
No description provided.
Homework 5 in CS287 of Harvard SEAS
Homework 4 in CS287 of Harvard SEAS
based on CharRnn by kaparthy
Homework 3 in CS287 of Harvard SEAS
Homework 2 in CS287 of Harvard SEAS
No description provided.
No description provided.
No description provided.