Unsupervised Pronoun Resolution via Masked Noun-Phrase Prediction
release_kraoujr3abcclislbyl7efbuoq
by
Ming Shen, Pratyay Banerjee, Chitta Baral
2021
Abstract
In this work, we propose Masked Noun-Phrase Prediction (MNPP), a pre-training
strategy to tackle pronoun resolution in a fully unsupervised setting. Firstly,
We evaluate our pre-trained model on various pronoun resolution datasets
without any finetuning. Our method outperforms all previous unsupervised
methods on all datasets by large margins. Secondly, we proceed to a few-shot
setting where we finetune our pre-trained model on WinoGrande-S and XS. Our
method outperforms RoBERTa-large baseline with large margins, meanwhile,
achieving a higher AUC score after further finetuning on the remaining three
official splits of WinoGrande.
In text/plain
format
Archived Files and Locations
application/pdf 377.2 kB
file_vrdyn657cncixgyqmk2fdtpmfa
|
arxiv.org (repository) web.archive.org (webarchive) |
2105.12392v1
access all versions, variants, and formats of this works (eg, pre-prints)