Autoencoding Improves Pre-trained Word Embeddings

v1v2 (latest)

Autoencoding Improves Pre-trained Word Embeddings

25 October 2020

Masahiro Kaneko

Danushka Bollegala

ArXiv (abs)PDF HTML

Papers citing "Autoencoding Improves Pre-trained Word Embeddings"

10 / 10 papers shown

Title
Exploring the Impact of a Transformer's Latent Space Geometry on Downstream Task Performance Anna C. Marbut John W. Chandler Travis J. Wheeler 81 0 0 18 Jun 2024
The Gaps between Pre-train and Downstream Settings in Bias Evaluation and Debiasing Masahiro Kaneko Danushka Bollegala Timothy Baldwin 74 3 0 16 Jan 2024
Comparing Intrinsic Gender Bias Evaluation Measures without using Human Annotated Examples Masahiro Kaneko Danushka Bollegala Naoaki Okazaki 60 10 0 28 Jan 2023
Reliable Measures of Spread in High Dimensional Latent Spaces Anna C. Marbut Katy McKinney-Bock Travis J. Wheeler 68 2 0 15 Dec 2022
Debiasing isn't enough! -- On the Effectiveness of Debiasing MLMs and their Social Biases in Downstream Tasks Masahiro Kaneko Danushka Bollegala Naoaki Okazaki 98 46 0 06 Oct 2022
Debiasing Word Embeddings with Nonlinear Geometry Lu Cheng Nayoung Kim Huan Liu 54 5 0 29 Aug 2022
Gender Bias in Meta-Embeddings Masahiro Kaneko Danushka Bollegala Naoaki Okazaki 69 6 0 19 May 2022
Unmasking the Mask -- Evaluating Social Biases in Masked Language Models Masahiro Kaneko Danushka Bollegala 63 72 0 15 Apr 2021
Dictionary-based Debiasing of Pre-trained Word Embeddings Masahiro Kaneko Danushka Bollegala FaML 97 38 0 23 Jan 2021
Debiasing Pre-trained Contextualised Embeddings Masahiro Kaneko Danushka Bollegala 269 143 0 23 Jan 2021