Abstract is missing.
- Distributionally Robust Recurrent Decoders with Random Network DistillationAntonio Valerio Miceli Barone, Alexandra Birch, Rico Sennrich. 1-8 [doi]
- Q-Learning Scheduler for Multi Task Learning Through the use of Histogram of Task UncertaintyKourosh Meshgi, Maryam Sadat Mirzaei, Satoshi Sekine. 9-19 [doi]
- PARADISE: Exploiting Parallel Data for Multilingual Sequence-to-Sequence PretrainingMachel Reid, Mikel Artetxe. 20-28 [doi]
- When does CLIP generalize better than unimodal models? When judging human-centric conceptsRomain Bielawski, Benjamin Devillers, Tim Van de Cruys, Rufin VanRullen. 29-38 [doi]
- From Hyperbolic Geometry Back to Word EmbeddingsZhenisbek Assylbekov, Sultan Nurmukhamedov, Arsen Sheverdin, Thomas Mach. 39-45 [doi]
- A Comparative Study of Pre-trained Encoders for Low-Resource Named Entity RecognitionYuxuan Chen, Jonas Mikkelsen, Arne Binder, Christoph Alt, Leonhard Hennig. 46-59 [doi]
- Clozer": " Adaptable Data Augmentation for Cloze-style Reading ComprehensionHoly Lovenia, Bryan Wilie, Willy Chung, Min Zeng, Samuel Cahyawijaya, Su Dan, Pascale Fung. 60-66 [doi]
- Analyzing Gender Representation in Multilingual ModelsHila Gonen, Shauli Ravfogel, Yoav Goldberg. 67-77 [doi]
- Detecting Textual Adversarial Examples Based on Distributional Characteristics of Data RepresentationsNa Liu, Mark Dras, Wei Emma Zhang. 78-90 [doi]
- A Vocabulary-Free Multilingual Neural Tokenizer for End-to-End Task LearningMd Mofijul Islam, Gustavo Aguilar, Pragaash Ponnusamy, Clint Solomon Mathialagan, Chengyuan Ma, Chenlei Guo. 91-99 [doi]
- Identifying the Limits of Cross-Domain Knowledge Transfer for Pretrained ModelsZhengxuan Wu, Nelson F. Liu, Christopher Potts. 100-110 [doi]
- Temporal Knowledge Graph Reasoning with Low-rank and Model-agnostic RepresentationsIoannis Dikeoulias, Saadullah Amin, Günter Neumann. 111-120 [doi]
- ANNA": " Enhanced Language Representation for Question AnsweringChangwook Jun, Hansol Jang, Myoseop Sim, Hyun Kim, Jooyoung Choi, Kyungkoo Min, Kyunghoon Bae. 121-132 [doi]
- Isomorphic Cross-lingual Embeddings for Low-Resource LanguagesSonal Sannigrahi, Jesse Read. 133-142 [doi]
- Video Language Co-Attention with Multimodal Fast-Learning Feature Fusion for VideoQAAdnen Abdessaied, Ekta Sood, Andreas Bulling. 143-155 [doi]
- Detecting Word-Level Adversarial Text Attacks via SHapley Additive exPlanationsEdoardo Mosca, Lukas Huber, Marc Alexander Kühn, Georg Groh. 156-166 [doi]
- Binary Encoded Word Mover's DistanceChristian Johnson. 167-172 [doi]
- Unsupervised Geometric and Topological Approaches for Cross-Lingual Sentence Representation and ComparisonShaked Haim Meirom, Omer Bobrowski. 173-183 [doi]
- A Study on Entity Linking Across Domains": " Which Data is Best for Fine-Tuning?Hassan Soliman, Heike Adel, Mohamed H. Gad-Elrab, Dragan Milchevski, Jannik Strötgen. 184-190 [doi]
- TRAttack": " Text Rewriting Attack Against Text RetrievalJunshuai Song, Jiangshan Zhang, Jifeng Zhu, Mengyun Tang, Yong Yang. 191-203 [doi]
- On the Geometry of ConcretenessChristian Wartena. 204-212 [doi]
- PALBERT: Teaching ALBERT to PonderDaniil Gavrilov, Nikita Balagansky. 213-220 [doi]
- Towards Improving Selective Prediction Ability of NLP SystemsNeeraj Varshney, Swaroop Mishra, Chitta Baral. 221-226 [doi]
- On Target Representation in Continuous-output Neural Machine TranslationEvgeniia Tokarchuk, Vlad Niculae. 227-235 [doi]
- Zero-shot Cross-lingual Transfer is Under-specified OptimizationShijie Wu, Benjamin Van Durme, Mark Dredze. 236-248 [doi]
- Same Author or Just Same Topic? Towards Content-Independent Style RepresentationsAnna Wegmann, Marijn Schraagen, Dong Nguyen 0002. 249-268 [doi]
- WeaNF: Weak Supervision with Normalizing FlowsAndreas Stephan, Benjamin Roth 0001. 269-279 [doi]