timoschick/am-for-bert timoschick/am-for-bert

  • Stars
    star
    14
  • Rank 1,438,076 (Top 29 %)
  • Language
    Python
  • Created over 5 years ago
  • Updated almost 5 years ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
timoschick/am-for-bert
github

timoschick

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

This repository contains the WordNet Language Model Probing (WNLaMPro) dataset introduced in "Rare Words: A Major Problem for Contextualized Embeddings and How to Fix it by Attentive Mimicking".

More Repositories

1

pet

This repository contains the code for "Exploiting Cloze Questions for Few-Shot Text Classification and Natural Language Inference"
Python
1,554
star
2

dino

This repository contains the code for "Generating Datasets with Pretrained Language Models".
Python
182
star
3

fewglue

This repository contains the FewGLUE dataset for few-shot natural language understanding.
158
star
4

self-debiasing

This repository contains the code for "Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP".
Python
75
star
5

bertram

This repository contains the code for "BERTRAM: Improved Word Embeddings Have Big Impact on Contextualized Representations".
Python
60
star
6

form-context-model

This repository contains the code for the Form-Context Model and its Attentive Mimicking variant.
Python
31
star
7

one-token-approximation

This repository contains the code for applying One-Token Approximation to a pretrained language model using subword-level tokenization.
Python
11
star
8

amr-gen

This is a Java-based implementation of the AMR-to-text generator introduced in "Transition-Based Generation from Abstract Meaning Representations".
Java
4
star