Transferability
Related Papers
Exploiting Invertible Decoders for Unsupervised Sentence Representation Learning
AbstractEncoder-decoder models for unsupervised sentence representation learning using the distributional hypothesis effectively constrain the learnt representation of a sentence to only that needed to reproduce the next sentence. While the …...
Generating Natural Language Adversarial Examples through Probability Weighted Word Saliency
AbstractWe address the problem of adversarial attacks on text classification, which is rarely studied comparing to attacks on image classification. The challenge of this task is to generate adversarial examples …...
T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted Attack
AbstractAdversarial attacks against natural language processing systems, which perform seemingly innocuous modifications to inputs, can induce arbitrary mistakes to the target models. Though raised great concerns, such adversarial attacks can …...
Word-level Textual Adversarial Attacking as Combinatorial Optimization
AbstractAdversarial attacks are carried out to reveal the vulnerability of deep neural networks. Textual adversarial attacking is challenging because text is discrete and a small perturbation can bring significant change …...
CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP
AbstractHumans can learn a new language task efficiently with only few examples, by leveraging their knowledge obtained when learning prior tasks. In this paper, we explore whether and how such …...
Do Language Models Perform Generalizable Commonsense Inference?
Inspired by evidence that pretrained language models (LMs) encode commonsense knowl- edge, recent work has applied LMs to auto- matically populate commonsense knowledge graphs (CKGs). However, there is a lack …...
Learning Universal Authorship Representations
AbstractDetermining whether two documents were composed by the same author, also known as authorship verification, has traditionally been tackled using statistical methods. Recently, authorship representations learned using neural networks have …...
ElitePLM: An Empirical Study on General Language Ability Evaluation of Pretrained Language Models
AbstractNowadays, pretrained language models (PLMs) have dominated the majority of NLP tasks. While, little research has been conducted on systematically evaluating the language abilities of PLMs. In this paper, we …...
On Transferability of Prompt Tuning for Natural Language Processing
AbstractPrompt tuning (PT) is a promising parameter-efficient method to utilize extremely large pre-trained language models (PLMs), which can achieve comparable performance to full-parameter fine-tuning by only tuning a few soft …...
Zero-shot Cross-lingual Transfer of Prompt-based Tuning with a Unified Multilingual Prompt
AbstractPrompt-based tuning has been proven effective for pretrained language models (PLMs). While most of the existing work focuses on the monolingual prompts, we study the multilingual prompts for multilingual PLMs, …...