English

Language Model Pre-Training with Sparse Latent Typing

Computation and Language 2022-10-28 v2 Artificial Intelligence

Abstract

Modern large-scale Pre-trained Language Models (PLMs) have achieved tremendous success on a wide range of downstream tasks. However, most of the LM pre-training objectives only focus on text reconstruction, but have not sought to learn latent-level interpretable representations of sentences. In this paper, we manage to push the language models to obtain a deeper understanding of sentences by proposing a new pre-training objective, Sparse Latent Typing, which enables the model to sparsely extract sentence-level keywords with diverse latent types. Experimental results show that our model is able to learn interpretable latent type categories in a self-supervised manner without using any external knowledge. Besides, the language model pre-trained with such an objective also significantly improves Information Extraction related downstream tasks in both supervised and few-shot settings. Our code is publicly available at: https://github.com/renll/SparseLT.

Keywords

Cite

@article{arxiv.2210.12582,
  title  = {Language Model Pre-Training with Sparse Latent Typing},
  author = {Liliang Ren and Zixuan Zhang and Han Wang and Clare R. Voss and Chengxiang Zhai and Heng Ji},
  journal= {arXiv preprint arXiv:2210.12582},
  year   = {2022}
}

Comments

EMNLP 2022 (Oral)

R2 v1 2026-06-28T04:16:19.488Z