paper-with-me

Papers

Improving Machine Reading Comprehension via Adversarial Training

2019-11-09 · Ziqing Yang, Yiming Cui, Wanxiang Che, Ting Liu, Shijin Wang, Guoping Hu

Adversarial training (AT) as a regularization method has proved its effectiveness in various tasks, such as image classification and text classification. Though there are successful applications of AT in many tasks of natural language processing (NLP), the mechanism behind it is still unclear. In this paper, we aim to apply AT on machine reading comprehension (MRC) and study its effects from multiple perspectives. We experiment with three different kinds of RC tasks: span-based RC, span-based RC with unanswerable questions and multi-choice RC. The experimental results show that the proposed method can improve the performance significantly and universally on SQuAD1.1, SQuAD2.0 and RACE. With virtual adversarial training (VAT), we explore the possibility of improving the RC models with semi-supervised learning and prove that examples from a different task are also beneficial. We also find that AT helps little in defending against artificial adversarial examples, but AT helps the model to learn better on examples that contain more low-frequency words.

📄 PDF Abstract BibTeX arXiv:1911.03614

Code (0)

등록된 구현이 없습니다.

Tasks

General Classificationimage-classificationImage ClassificationMachine Reading ComprehensionReading Comprehensiontext-classificationText Classification

Similar Papers 제목 키워드 기반

Stochastic Answer Networks for Machine Reading Comprehension

2017-12-10 · ACL 2018 7 · Xiaodong Liu, Yelong Shen, Kevin Duh, Jianfeng Gao

We propose a simple yet robust stochastic answer network (SAN) that simulates multi-step reasoning in machine reading comprehension. Compared to previous work such as ReasoNet which used reinforcement learning to determi…

Machine Reading ComprehensionQuestion AnsweringReading Comprehensionreinforcement-learning+2

Adversarial Training for Machine Reading Comprehension with Virtual Embeddings

2021-06-08 · Joint Conference on Lexical and Computational Semantics 2021 · Ziqing Yang, Yiming Cui, Chenglei Si, Wanxiang Che 외

Adversarial training (AT) as a regularization method has proved its effectiveness on various tasks. Though there are successful applications of AT on some NLP tasks, the distinguishing characteristics of NLP tasks have n…

Machine Reading ComprehensionMultiple-choiceReading Comprehension

Adversarial reading networks for machine comprehension

2018-01-01 · ICLR 2018 1 · Quentin Grail, julien perez

Machine reading has recently shown remarkable progress thanks to differentiable reasoning models. In this context, End-to-End trainable Memory Networks (MemN2N) have demonstrated promising performance on simple natural l…

Machine Reading ComprehensionQuestion AnsweringReading Comprehension

Power in Numbers: Robust reading comprehension by finetuning with four adversarial sentences per example

2024-01-18 · Ariel Marcus

Recent models have achieved human level performance on the Stanford Question Answering Dataset when using F1 scores to evaluate the reading comprehension task. Yet, teaching machines to comprehend text has not been solve…

Question AnsweringReading ComprehensionSentence

Dataset for the First Evaluation on Chinese Machine Reading Comprehension

2017-09-25 · LREC 2018 5 · Yiming Cui, Ting Liu, Zhipeng Chen, Wentao Ma 외

Machine Reading Comprehension (MRC) has become enormously popular recently and has attracted a lot of attention. However, existing reading comprehension datasets are mostly in English. To add diversity in reading compreh…

Chinese Reading ComprehensionDiversityMachine Reading ComprehensionReading Comprehension