 Generate (non-software) Bugs to Fool ClassifiersAAAI Conference on Artificial Intelligence (AAAI), 2019 |
 Robust Reading Comprehension with Linguistic Constraints via Posterior
RegularizationIEEE/ACM Transactions on Audio Speech and Language Processing (TASLP), 2019 |
 Ask to Learn: A Study on Curiosity-driven Question GenerationInternational Conference on Computational Linguistics (COLING), 2019 |
 The TechQA DatasetAnnual Meeting of the Association for Computational Linguistics (ACL), 2019 |
 Adversarial Language Games for Advanced Natural Language IntelligenceAAAI Conference on Artificial Intelligence (AAAI), 2019 Xingtai Lv Haoxiang Zhong Zhengyan Zhang Xu Han Xiaozhi Wang Chaojun Xiao Guoyang Zeng Zhiyuan Liu Maosong Sun |
 Posing Fair Generalization Tasks for Natural Language InferenceConference on Empirical Methods in Natural Language Processing (EMNLP), 2019 |
 Security of Facial Forensics Models Against Adversarial AttacksInternational Conference on Information Photonics (ICIP), 2019 |
 Adversarial NLI: A New Benchmark for Natural Language UnderstandingAnnual Meeting of the Association for Computational Linguistics (ACL), 2019 |
 Relation Module for Non-answerable Prediction on Question AnsweringConference on Computational Natural Language Learning (CoNLL), 2019 |
 MRQA 2019 Shared Task: Evaluating Generalization in Reading
ComprehensionConference on Empirical Methods in Natural Language Processing (EMNLP), 2019 |
 Man-in-the-Middle Attacks against Machine Learning Classifiers via
Malicious Generative ModelsIEEE Transactions on Dependable and Secure Computing (TDSC), 2019 |
 Topic-aware Pointer-Generator Networks for Summarizing Spoken
ConversationsAutomatic Speech Recognition & Understanding (ASRU), 2019 |
 Learning the Difference that Makes a Difference with
Counterfactually-Augmented DataInternational Conference on Learning Representations (ICLR), 2019 |
 FreeLB: Enhanced Adversarial Training for Natural Language UnderstandingInternational Conference on Learning Representations (ICLR), 2019 |
 An Empirical Study of Content Understanding in Conversational Question
AnsweringAAAI Conference on Artificial Intelligence (AAAI), 2019 |
 Procedural Reasoning Networks for Understanding Multimodal ProceduresConference on Computational Natural Language Learning (CoNLL), 2019 |
 Adversarial Attacks and Defenses in Images, Graphs and Text: A ReviewInternational Journal of Automation and Computing (IJAC), 2019 |
 Addressing Semantic Drift in Question Generation for Semi-Supervised
Question AnsweringConference on Empirical Methods in Natural Language Processing (EMNLP), 2019 |
 End-to-End Bias Mitigation by Modelling Biases in CorporaAnnual Meeting of the Association for Computational Linguistics (ACL), 2019 |
 Retrofitting Contextualized Word Embeddings with ParaphrasesConference on Empirical Methods in Natural Language Processing (EMNLP), 2019 |
 Analyzing machine-learned representations: A natural language case studyCognitive Sciences (CS), 2019 |
 Finding Generalizable Evidence by Learning to Convince Q&A ModelsConference on Empirical Methods in Natural Language Processing (EMNLP), 2019 |
 Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known
Dataset BiasesConference on Empirical Methods in Natural Language Processing (EMNLP), 2019 |
 Semantics-aware BERT for Language UnderstandingAAAI Conference on Artificial Intelligence (AAAI), 2019 |
 Achieving Verified Robustness to Symbol Substitutions via Interval Bound
PropagationConference on Empirical Methods in Natural Language Processing (EMNLP), 2019 |
 Certified Robustness to Adversarial Word SubstitutionsConference on Empirical Methods in Natural Language Processing (EMNLP), 2019 |
 QAInfomax: Learning Robust Question Answering System by Mutual
Information MaximizationConference on Empirical Methods in Natural Language Processing (EMNLP), 2019 |
 A Logic-Driven Framework for Consistency of Neural ModelsConference on Empirical Methods in Natural Language Processing (EMNLP), 2019 |
 PAWS-X: A Cross-lingual Adversarial Dataset for Paraphrase
IdentificationConference on Empirical Methods in Natural Language Processing (EMNLP), 2019 |
 Detecting and Reducing Bias in a High Stakes DomainConference on Empirical Methods in Natural Language Processing (EMNLP), 2019 |
 Interactive Language Learning by Question AnsweringConference on Empirical Methods in Natural Language Processing (EMNLP), 2019 |
 Unlearn Dataset Bias in Natural Language Inference by Fitting the
ResidualConference on Empirical Methods in Natural Language Processing (EMNLP), 2019 |
 Evaluating Defensive Distillation For Defending Text Processing Neural
Networks Against Adversarial ExamplesInternational Conference on Artificial Neural Networks (ICANN), 2019 |
 Universal Adversarial Triggers for Attacking and Analyzing NLPConference on Empirical Methods in Natural Language Processing (EMNLP), 2019 |
 Build it Break it Fix it for Dialogue Safety: Robustness from
Adversarial Human AttackConference on Empirical Methods in Natural Language Processing (EMNLP), 2019 |
 CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from TextConference on Empirical Methods in Natural Language Processing (EMNLP), 2019 |
 Towards Debiasing Fact Verification ModelsConference on Empirical Methods in Natural Language Processing (EMNLP), 2019 |
 Mitigating Noisy Inputs for Question AnsweringInterspeech (Interspeech), 2019 |
