| DOCmT5: Document-Level Pretraining of Multilingual Language Models | Dec 16, 2021 | de-enDocument Summarization | —Unverified | 0 |
| Idiomatic Expression Paraphrasing without Strong Supervision | Dec 16, 2021 | Machine TranslationSentence | —Unverified | 0 |
| PECO: Examining Single Sentence Label Leakage in Natural Language Inference Datasets through Progressive Evaluation of Cluster Outliers | Dec 16, 2021 | Natural Language InferenceSentence | —Unverified | 0 |
| A Deep Learning Approach for Ontology Enrichment from Unstructured Text | Dec 16, 2021 | Anomaly DetectionDeep Learning | —Unverified | 0 |
| Bridging between Cognitive Processing Signals and Linguistic Features via a Unified Attentional Network | Dec 16, 2021 | Sentence | —Unverified | 0 |
| ALP: Data Augmentation using Lexicalized PCFGs for Few-Shot Text Classification | Dec 16, 2021 | ClassificationData Augmentation | —Unverified | 0 |
| Isochrony-Aware Neural Machine Translation for Automatic Dubbing | Dec 16, 2021 | Machine TranslationSentence | —Unverified | 0 |
| Simple Text Detoxification by Identifying a Linear Toxic Subspace in Language Model Embeddings | Dec 15, 2021 | Abusive LanguageLanguage Modeling | —Unverified | 0 |
| Tracing Text Provenance via Context-Aware Lexical Substitution | Dec 15, 2021 | Optical Character Recognition (OCR)Sentence | —Unverified | 0 |
| Cross-Domain Generalization and Knowledge Transfer in Transformers Trained on Legal Data | Dec 15, 2021 | Domain GeneralizationSentence | —Unverified | 0 |
