Putting Words in BERT's Mouth: Navigating Contextualized Vector Spaces with Pseudowords

This repository contains the code of our paper Putting Words in BERT's Mouth: Navigating Contextualized Vector Spaces with Pseudowords (EMNLP 2021).

MaPP Dataset

The dataset can be found here. It is devided to 3 portions (as we describe in our paper).

Get Pseudowords

To get the pseudoword vectors, run the code --> get_pseudowords.py using the data (queries) we provide here, or data of the same format.

Citation

Please cite our paper if you found the resources in this repository useful.

inproceedings{karidi2021putting,
    title = "Putting Words in BERT's Mouth: Navigating Contextualized Vector Spaces with Pseudowords,
    author = "Taelin Karidi and Yichu Zhou and Nathan Schneider and Omri Abend and Vivek Srikumar",
    booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
    month = oct,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/2109.11491",
    

}