Title |
|---|
 BERTs of a feather do not generalize together: Large variability in
generalization across models with similar test set performanceBlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackBoxNLP), 2019 |
 On the Linguistic Representational Power of Neural Machine Translation
ModelsInternational Conference on Computational Logic (ICCL), 2019 |
 A Neural Entity Coreference Resolution ReviewExpert systems with applications (ESWA), 2019 |
 Diversify Your Datasets: Analyzing Generalization via Controlled
Variance in Adversarial DatasetsConference on Computational Natural Language Learning (CoNLL), 2019 |
 Discovering the Compositional Structure of Vector Representations with
Role Learning NetworksBlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackBoxNLP), 2019 |
 Specializing Word Embeddings (for Parsing) by Information BottleneckConference on Empirical Methods in Natural Language Processing (EMNLP), 2019 Xiang Lisa Li Jason Eisner |
 Graph Convolutions over Constituent Trees for Syntax-Aware Semantic Role
LabelingConference on Empirical Methods in Natural Language Processing (EMNLP), 2019 |
 How Does BERT Answer Questions? A Layer-Wise Analysis of Transformer
RepresentationsInternational Conference on Information and Knowledge Management (CIKM), 2019 |
 Designing and Interpreting Probes with Control TasksConference on Empirical Methods in Natural Language Processing (EMNLP), 2019 |
 Effective Use of Transformer Networks for Entity TrackingConference on Empirical Methods in Natural Language Processing (EMNLP), 2019 |
 MoverScore: Text Generation Evaluating with Contextualized Embeddings
and Earth Mover DistanceConference on Empirical Methods in Natural Language Processing (EMNLP), 2019 |
 Investigating BERT's Knowledge of Language: Five Analysis Methods with
NPIsConference on Empirical Methods in Natural Language Processing (EMNLP), 2019 |
 Investigating Multilingual NMT Representations at ScaleConference on Empirical Methods in Natural Language Processing (EMNLP), 2019 |
 The Bottom-up Evolution of Representations in the Transformer: A Study
with Machine Translation and Language Modeling ObjectivesConference on Empirical Methods in Natural Language Processing (EMNLP), 2019 |
 Language Models as Knowledge Bases?Conference on Empirical Methods in Natural Language Processing (EMNLP), 2019 |
 How Contextual are Contextualized Word Representations? Comparing the
Geometry of BERT, ELMo, and GPT-2 EmbeddingsConference on Empirical Methods in Natural Language Processing (EMNLP), 2019 |
 Higher-order Comparisons of Sentence Encoder RepresentationsConference on Empirical Methods in Natural Language Processing (EMNLP), 2019 |
 Evaluation Benchmarks and Learning Criteria for Discourse-Aware Sentence
RepresentationsConference on Empirical Methods in Natural Language Processing (EMNLP), 2019 |
 Learning Latent Parameters without Human Response Patterns: Item
Response Theory with Artificial CrowdsConference on Empirical Methods in Natural Language Processing (EMNLP), 2019 |
 Compositionality decomposed: how do neural networks generalise?Journal of Artificial Intelligence Research (JAIR), 2019 |
 Deep Contextualized Word Embeddings in Transition-Based and Graph-Based
Dependency Parsing -- A Tale of Two Parsers RevisitedConference on Empirical Methods in Natural Language Processing (EMNLP), 2019 |
 Visualizing and Understanding the Effectiveness of BERTConference on Empirical Methods in Natural Language Processing (EMNLP), 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 |
 Multi-Task Learning for Coherence ModelingAnnual Meeting of the Association for Computational Linguistics (ACL), 2019 |
 A Survey of Reinforcement Learning Informed by Natural LanguageInternational Joint Conference on Artificial Intelligence (IJCAI), 2019 |
 Encouraging Paragraph Embeddings to Remember Sentence Identity Improves
ClassificationAnnual Meeting of the Association for Computational Linguistics (ACL), 2019 |
 Probing for Semantic Classes: Diagnosing the Meaning Content of Word
EmbeddingsAnnual Meeting of the Association for Computational Linguistics (ACL), 2019 |
 Visualizing and Measuring the Geometry of BERTNeural Information Processing Systems (NeurIPS), 2019 |
 Entity-Centric Contextual Affective AnalysisAnnual Meeting of the Association for Computational Linguistics (ACL), 2019 |
 How multilingual is Multilingual BERT?Annual Meeting of the Association for Computational Linguistics (ACL), 2019 |
 Assessing the Ability of Self-Attention Networks to Learn Word OrderAnnual Meeting of the Association for Computational Linguistics (ACL), 2019 |
 AMR Parsing as Sequence-to-Graph TransductionAnnual Meeting of the Association for Computational Linguistics (ACL), 2019 |
 BERT Rediscovers the Classical NLP PipelineAnnual Meeting of the Association for Computational Linguistics (ACL), 2019 |
 Correlating neural and symbolic representations of languageAnnual Meeting of the Association for Computational Linguistics (ACL), 2019 |
 SuperGLUE: A Stickier Benchmark for General-Purpose Language
Understanding SystemsNeural Information Processing Systems (NeurIPS), 2019 |
