paper-with-me

Papers

Ignore Me But Don't Replace Me: Utilizing Non-Linguistic Elements for Pretraining on the Cybersecurity Domain

2024-03-15 · Eugene Jang, Jian Cui, Dayeon Yim, Youngjin Jin, Jin-Woo Chung, Seungwon Shin, YongJae lee

Cybersecurity information is often technically complex and relayed through unstructured text, making automation of cyber threat intelligence highly challenging. For such text domains that involve high levels of expertise, pretraining on in-domain corpora has been a popular method for language models to obtain domain expertise. However, cybersecurity texts often contain non-linguistic elements (such as URLs and hash values) that could be unsuitable with the established pretraining methodologies. Previous work in other domains have removed or filtered such text as noise, but the effectiveness of these methods have not been investigated, especially in the cybersecurity domain. We propose different pretraining methodologies and evaluate their effectiveness through downstream tasks and probing tasks. Our proposed strategy (selective MLM and jointly training NLE token classification) outperforms the commonly taken approach of replacing non-linguistic elements (NLEs). We use our domain-customized methodology to train CyBERTuned, a cybersecurity domain language model that outperforms other cybersecurity PLMs on most tasks.

📄 PDF Abstract BibTeX arXiv:2403.10576

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage Modellingtoken-classificationToken Classification

Similar Papers 제목 키워드 기반

Frustratingly Simple Pretraining Alternatives to Masked Language Modeling

2021-09-04 · EMNLP 2021 11 · Atsuki Yamaguchi, George Chrysostomou, Katerina Margatina, Nikolaos Aletras

Masked language modeling (MLM), a self-supervised pretraining objective, is widely used in natural language processing for learning text representations. MLM trains a model to predict a random sample of input tokens that…

Language ModelingLanguage ModellingMasked Language ModelingSentence

Dense Contrastive Visual-Linguistic Pretraining

2021-09-24 · Lei Shi, Kai Shuang, Shijie Geng, Peng Gao 외

Inspired by the success of BERT, several multimodal representation learning approaches have been proposed that jointly represent image and text. These approaches achieve superior performance by capturing high-level seman…

Contrastive LearningData AugmentationregressionRepresentation Learning

Identifying Necessary Elements for BERT's Multilinguality

2020-05-01 · Philipp Dufter, Hinrich Schütze

It has been shown that multilingual BERT (mBERT) yields high quality multilingual representations and enables effective zero-shot transfer. This is surprising given that mBERT does not use any crosslingual signal during …

Identifying Elements Essential for BERT's Multilinguality

2020-11-01 · EMNLP 2020 11 · Philipp Dufter, Hinrich Sch{\"u}tze

It has been shown that multilingual BERT (mBERT) yields high quality multilingual representations and enables effective zero-shot transfer. This is surprising given that mBERT does not use any crosslingual signal during …

UnihanLM: Coarse-to-Fine Chinese-Japanese Language Model Pretraining with the Unihan Database

2020-12-01 · Asian Chapter of the Association for Computational Linguistics 2020 · Canwen Xu, Tao Ge, Chenliang Li, Furu Wei

Chinese and Japanese share many characters with similar surface morphology. To better utilize the shared knowledge across the languages, we propose UnihanLM, a self-supervised Chinese-Japanese pretrained masked language …

Language ModelingLanguage Modelling