 StructBERT: Incorporating Language Structures into Pre-training for Deep
Language UnderstandingInternational Conference on Learning Representations (ICLR), 2019 |
 On Identifiability in TransformersInternational Conference on Learning Representations (ICLR), 2019 |
 What BERT is not: Lessons from a new suite of psycholinguistic
diagnostics for language modelsTransactions of the Association for Computational Linguistics (TACL), 2019 |
 ERNIE 2.0: A Continual Pre-training Framework for Language UnderstandingAAAI Conference on Artificial Intelligence (AAAI), 2019 |
 A Hybrid Neural Network Model for Commonsense ReasoningConference on Empirical Methods in Natural Language Processing (EMNLP), 2019 |
 Careful Selection of Knowledge to solve Open Book Question AnsweringAnnual Meeting of the Association for Computational Linguistics (ACL), 2019 |
 Generic Intent Representation in Web SearchAnnual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2019 |
 SpanBERT: Improving Pre-training by Representing and Predicting SpansTransactions of the Association for Computational Linguistics (TACL), 2019 |
 |
 A Pragmatics-Centered Evaluation Framework for Natural Language
UnderstandingInternational Conference on Language Resources and Evaluation (LREC), 2019 |
 BAM! Born-Again Multi-Task Networks for Natural Language UnderstandingAnnual Meeting of the Association for Computational Linguistics (ACL), 2019 |
 Large Memory Layers with Product KeysNeural Information Processing Systems (NeurIPS), 2019 |
 Don't Take the Premise for Granted: Mitigating Artifacts in Natural
Language InferenceAnnual Meeting of the Association for Computational Linguistics (ACL), 2019 |
 XLNet: Generalized Autoregressive Pretraining for Language UnderstandingNeural Information Processing Systems (NeurIPS), 2019 |
 Evaluating Protein Transfer Learning with TAPEbioRxiv (bioRxiv), 2019 |
 Unsupervised State Representation Learning in AtariNeural Information Processing Systems (NeurIPS), 2019 |
 A Simple and Effective Approach to Automatic Post-Editing with Transfer
LearningAnnual Meeting of the Association for Computational Linguistics (ACL), 2019 Gonçalo M. Correia André F. T. Martins |
 Continual and Multi-Task Architecture SearchAnnual Meeting of the Association for Computational Linguistics (ACL), 2019 |
 Explain Yourself! Leveraging Language Models for Commonsense ReasoningAnnual Meeting of the Association for Computational Linguistics (ACL), 2019 |
 Topic Sensitive Attention on Generic Corpora Corrects Sense Bias in
Pretrained EmbeddingsAnnual Meeting of the Association for Computational Linguistics (ACL), 2019 |
 Pretraining Methods for Dialog Context Representation LearningAnnual Meeting of the Association for Computational Linguistics (ACL), 2019 |
 MultiQA: An Empirical Investigation of Generalization and Transfer in
Reading ComprehensionAnnual Meeting of the Association for Computational Linguistics (ACL), 2019 |
 A Compare-Aggregate Model with Latent Clustering for Answer SelectionInternational Conference on Information and Knowledge Management (CIKM), 2019 |
 Defending Against Neural Fake NewsNeural Information Processing Systems (NeurIPS), 2019 |
 DDPNAS: Efficient Neural Architecture Search via Dynamic Distribution
PruningInternational Journal of Computer Vision (IJCV), 2019 |
 Human vs. Muppet: A Conservative Estimate of Human Performance on the
GLUE BenchmarkAnnual Meeting of the Association for Computational Linguistics (ACL), 2019 |
 BoolQ: Exploring the Surprising Difficulty of Natural Yes/No QuestionsNorth American Chapter of the Association for Computational Linguistics (NAACL), 2019 |
 Hangul Fonts Dataset: a Hierarchical and Compositional Dataset for
Investigating Learned RepresentationsInternational Conference on Image Analysis and Processing (ICIAP), 2019 |
 Story Ending Prediction by Transferable BERTInternational Joint Conference on Artificial Intelligence (IJCAI), 2019 |
 ERNIE: Enhanced Language Representation with Informative EntitiesAnnual Meeting of the Association for Computational Linguistics (ACL), 2019 |
 What do you learn from context? Probing for sentence structure in
contextualized word representationsInternational Conference on Learning Representations (ICLR), 2019 |
 A Surprisingly Robust Trick for Winograd Schema ChallengeAnnual Meeting of the Association for Computational Linguistics (ACL), 2019 |
 Survey on Evaluation Methods for Dialogue SystemsArtificial Intelligence Review (AIR), 2019 |
 Unified Language Model Pre-training for Natural Language Understanding
and GenerationNeural Information Processing Systems (NeurIPS), 2019 |
