Jacob Hotz's starred repositories
sentence-transformers
Multilingual Sentence & Image Embeddings with BERT
bert_score
BERT score for text generation
attention-cnn
Source code for "On the Relationship between Self-Attention and Convolutional Layers"
pytorch-apple-silicon
Setup PyTorch on Mac/Apple Silicon plus a few benchmarks.
mlm-scoring
Python library & examples for Masked Language Model Scoring (ACL 2020)
electra-pytorch
A simple and working implementation of Electra, the fastest way to pretrain language models from scratch, in Pytorch
commonsenseqa
Author implementation of the paper "CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge"
Zero-Shot-DST
Zero-shot dialogue state tracking (DST)
ACL2020-ConKADI
Resources for the our ACL2020 paper, Diverse and Informative Dialogue Generation with Context-Specific Commonsense Knowledge Awareness
discourse_probing
Discourse Probing of Pretrained Language Models. In Proceedings of NAACL 2021.
detecting_wsd_biases_for_nmt
Repository containing the experimental code for the publication 'Detecting Word Sense Disambiguation Biases in Machine Translation for Model-Agnostic Adversarial Attacks' (Emelin, Denis, Ivan Titov, and Rico Sennrich, EMNLP 2020).
Pre-Training-is-almost-all-you-Need-for-Commonsense-Reasoning
An (as efficient as possible) implementation of the paper "Pre-training Is (Almost) All You Need: An Application to Commonsense Reasoning"