Log In Sign Up

Model Agnostic Answer Reranking System for Adversarial Question Answering

by   Sagnik Majumder, et al.

While numerous methods have been proposed as defenses against adversarial examples in question answering (QA), these techniques are often model specific, require retraining of the model, and give only marginal improvements in performance over vanilla models. In this work, we present a simple model-agnostic approach to this problem that can be applied directly to any QA model without any retraining. Our method employs an explicit answer candidate reranking mechanism that scores candidate answers on the basis of their content overlap with the question before making the final prediction. Combined with a strong base QAmodel, our method outperforms state-of-the-art defense techniques, calling into question how well these techniques are actually doing and strong these adversarial testbeds are.


page 1

page 2

page 3

page 4


Domain-agnostic Question-Answering with Adversarial Training

Adapting models to new domain without finetuning is a challenging proble...

Will this Question be Answered? Question Filtering via Answer Model Distillation for Efficient Question Answering

In this paper we propose a novel approach towards improving the efficien...

TASA: Deceiving Question Answering Models by Twin Answer Sentences Attack

We present Twin Answer Sentences Attack (TASA), an adversarial attack me...

Robust Question Answering Through Sub-part Alignment

Current textual question answering models achieve strong performance on ...

Improving Lexical Embeddings for Robust Question Answering

Recent techniques in Question Answering (QA) have gained remarkable perf...

Matching Questions and Answers in Dialogues from Online Forums

Matching question-answer relations between two turns in conversations is...