Abstract is missing.
- Domain adaptation challenges of BERT in tokenization and sub-word representations of Out-of-Vocabulary wordsAnmol Nayak, Hariprasad Timmapathini, Karthikeyan Ponnalagu, Vijendran Gopalan Venkoparao. 1-5 [doi]
- Q. Can Knowledge Graphs be used to Answer Boolean Questions? A. It's complicated!Daria Dzendzik, Carl Vogel, Jennifer Foster. 6-14 [doi]
- How Far Can We Go with Data Selection? A Case Study on Semantic Sequence Tagging TasksSamuel Louvan, Bernardo Magnini. 15-21 [doi]
- Evaluating the Effectiveness of Efficient Neural Architecture Search for Sentence-Pair TasksAnsel MacLaughlin, Jwala Dhamala, Anoop Kumar, Sriram Venkatapathy, Ragav Venkatesan, Rahul Gupta. 22-31 [doi]
- Which Matters Most? Comparing the Impact of Concept and Document Relationships in Topic ModelsSilvia Terragni, Debora Nozza, Elisabetta Fersini, Enza Messina. 32-40 [doi]
- On Task-Level Dialogue Composition of Generative Transformer ModelPrasanna Parthasarathi, Sharan Narang, Arvind Neelakantan. 41-47 [doi]
- How Effectively Can Machines Defend Against Machine-Generated Fake News? An Empirical StudyMeghana Moorthy Bhat, Srinivasan Parthasarathy 0001. 48-53 [doi]
- Label Propagation-Based Semi-Supervised Learning for Hate Speech ClassificationAshwin Geet D'Sa, Irina Illina, Dominique Fohr, Dietrich Klakow, Dana Ruiter. 54-59 [doi]
- Layout-Aware Text Representations Harm Clustering Documents by TypeCatherine Finegan-Dollak, Ashish Verma. 60-65 [doi]
- An Analysis of Capsule Networks for Part of Speech Tagging in High- and Low-resource ScenariosAndrew Zupon, Faiz Rafique, Mihai Surdeanu. 66-70 [doi]
- Can Knowledge Graph Embeddings Tell Us What Fact-checked Claims Are About?Valentina Beretta, Sébastien Harispe, Katarina Boland, Luke Lo Seen, Konstantin Todorov, Andon Tchechmedjiev. 71-75 [doi]
- Do Transformers Dream of Inference, or Can Pretrained Generative Models Learn Implicit Inferential Rules?Zhengzhong Liang, Mihai Surdeanu. 76-81 [doi]
- Counterfactually-Augmented SNLI Training Data Does Not Yield Better Generalization Than Unaugmented DataWilliam Huang, Haokun Liu, Samuel R. Bowman. 82-87 [doi]
- NMF Ensembles? Not for Text Summarization!Alka Khurana, Vasudha Bhatnagar. 88-93 [doi]
- If You Build Your Own NER Scorer, Non-replicable Results Will ComeConstantine Lignos, Marjan Kamyab. 94-99 [doi]
- HINT3: Raising the bar for Intent Detection in the WildGaurav Arora, Chirag Jain, Manas Chaturvedi, Krupal Modi. 100-105 [doi]
- The Extraordinary Failure of Complement Coercion CrowdsourcingYanai Elazar, Victoria Basmova, Shauli Ravfogel, Yoav Goldberg, Reut Tsarfaty. 106-116 [doi]
- Embedding Structured Dictionary EntriesSteven R. Wilson 0001, Walid Magdy, Barbara McGillivray, Gareth Tyson. 117-125 [doi]