Table of Contents

• Transfer Learning for Humor Detection by Twin Masked Yellow MuppetsAseem Arora, Gaël Dias, Adam Jatowt, Asif Ekbal. 1-7 [doi]
• A Unified Model for Reverse Dictionary and Definition ModellingPinzhen Chen, Zheng Zhao. 8-13 [doi]
• Benchmarking the Covariate Shift Robustness of Open-world Intent Classification ApproachesSopan Khosla, Rashmi Gangadharaiah. 14-23 [doi]
• Number Theory Meets Linguistics: Modelling Noun Pluralisation Across 1497 Languages Using 2-adic MetricsGregory Baker, Diego Mollá. 24-32 [doi]
• CLIP4IDC: CLIP for Image Difference CaptioningZixin Guo, Tzu-Jui Julius Wang, Jorma Laaksonen. 33-42 [doi]
• Towards Modeling Role-Aware Centrality for Dialogue SummarizationXinnian Liang, Chao Bian, Shuangzhi Wu, Zhoujun Li 0001. 43-50 [doi]
• Robust Hate Speech Detection via Mitigating Spurious CorrelationsKshitiz Tiwari, Shuhan Yuan, Lu Zhang. 51-56 [doi]
• FAD-X: Fusing Adapters for Cross-lingual Transfer to Low-Resource LanguagesJaeseong Lee 0002, Seung-won Hwang, Taesup Kim. 57-64 [doi]
• Combining Argumentation Structure and Language Model for Generating Natural Argumentative DialogueKoh Mitsuda, Ryuichiro Higashinaka, Kuniko Saito. 65-71 [doi]
• Every word counts: A multilingual analysis of individual human alignment with model attentionStephanie Brandl, Nora Hollenstein. 72-77 [doi]
• Analyzing Biases to Spurious Correlations in Text Classification TasksAdian Liusie, Vatsal Raina, Vyas Raina, Mark J. F. Gales. 78-84 [doi]
• BERTSeg: BERT Based Unsupervised Subword Segmentation for Neural Machine TranslationHaiyue Song, Raj Dabre, Zhuoyuan Mao, Chenhui Chu, Sadao Kurohashi. 85-94 [doi]
• NERDz: A Preliminary Dataset of Named Entities for AlgerianSamia Touileb. 95-101 [doi]
• An Effective Post-training Embedding Binarization Approach for Fast Online Top-K Passage MatchingYankai Chen 0001, Yifei Zhang, Huifeng Guo, Ruiming Tang, Irwin King. 102-108 [doi]
• Addressing Segmentation Ambiguity in Neural Linguistic SteganographyJumon Nozaki, Yugo Murawaki. 109-116 [doi]
• Parsing linearizations appreciate PoS tags - but some are fussy about errorsAlberto Muñoz-Ortiz, Mark Anderson 0005, David Vilares, Carlos Gómez-Rodríguez. 117-127 [doi]
• EmoNoBa: A Dataset for Analyzing Fine-Grained Emotions on Noisy Bangla TextsKhondoker Ittehadul Islam, Tanvir Yuvraz, Md Saiful Islam, Enamul Hassan. 128-134 [doi]
• Exploring Universal Sentence Encoders for Zero-shot Text ClassificationSouvika Sarkar, Dongji Feng, Shubhra Kanti Karmaker Santu. 135-147 [doi]
• The Effects of Language Token Prefixing for Multilingual Machine TranslationRachel Wicks, Kevin D. Shockley. 148-153 [doi]
• How Relevant is Selective Memory Population in Lifelong Language Learning?Vladimir Araujo, Helena Balabin, Julio Hurtado, Alvaro Soto, Marie-Francine Moens. 154-160 [doi]
• An Improved Baseline for Sentence-level Relation ExtractionWenxuan Zhou, Muhao Chen. 161-168 [doi]
• Multi-Type Conversational Question-Answer Generation with Closed-ended and Unanswerable QuestionsSeonjeong Hwang, Yunsu Kim 0001, Gary Geunbae Lee. 169-177 [doi]
• Improving Chinese Story Generation via Awareness of Syntactic Dependencies and SemanticsHenglin Huang, Chen Tang, Tyler Loakman, Frank Guerin, Chenghua Lin. 178-185 [doi]
• NGEP: A Graph-based Event Planning Framework for Story GenerationChen Tang, Zhihao Zhang, Tyler Loakman, Chenghua Lin, Frank Guerin. 186-193 [doi]
• A Simple Yet Effective Hybrid Pre-trained Language Model for Unsupervised Sentence Acceptability PredictionYang Zhao, Issei Yoshida. 194-201 [doi]
• Post-Training with Interrogative Sentences for Enhancing BART-based Korean Question GeneratorGyu-Min Park, Seong-Eun Hong, Seong-Bae Park. 202-209 [doi]
• Do ever larger octopi still amplify reporting biases? Evidence from judgments of typical colourFangyu Liu 0001, Julian Eisenschlos, Jeremy R. Cole, Nigel Collier. 210-220 [doi]
• Adversarially Improving NMT Robustness to ASR Errors with Confusion SetsShuaibo Wang, Yufeng Chen 0005, Songming Zhang, Deyi Xiong, Jinan Xu. 221-227 [doi]
• Improving Graph-Based Text Representations with Character and Word Level N-gramsWenzhe Li, Nikolaos Aletras. 228-233 [doi]
• Risk-graded Safety for Handling Medical Queries in Conversational AIGavin Abercrombie, Verena Rieser. 234-243 [doi]
• Performance-Efficiency Trade-Offs in Adapting Language Models to Text Classification TasksLaura Aina, Nikos Voskarides, Roi Blanco. 244-253 [doi]
• Seeking Diverse Reasoning Logic: Controlled Equation Expression Generation for Solving Math Word ProblemsYibin Shen, Qianying Liu, Zhuoyuan Mao, Zhen Wan, Fei Cheng, Sadao Kurohashi. 254-260 [doi]
• BanglaParaphrase: A High-Quality Bangla Paraphrase DatasetAjwad Akil, Najrin Sultana, Abhik Bhattacharjee, Rifat Shahriyar. 261-272 [doi]
• NepBERTa: Nepali Language Model Trained in a Large CorpusSulav Timilsina, Milan Gautam, Binod Bhattarai. 273-284 [doi]
• Local Structure Matters Most in Most LanguagesLouis Clouâtre, Prasanna Parthasarathi, Amal Zouaq, Sarath Chandar. 285-294 [doi]
• Transformer-based Localization from Embodied Dialog with Large-scale Pre-trainingMeera Hahn, James M. Rehg. 295-301 [doi]
• CSS: Combining Self-training and Self-supervised Learning for Few-shot Dialogue State TrackingHaoning Zhang, Junwei Bao 0001, Haipeng Sun, Huaishao Luo, Wenye Li 0001, Shuguang Cui. 302-310 [doi]
• Demographic-Aware Language Model Fine-tuning as a Bias Mitigation TechniqueAparna Garimella, Rada Mihalcea, Akhash Amarnath. 311-319 [doi]
• Towards Simple and Efficient Task-Adaptive Pre-training for Text ClassificationArnav Ladkat, Aamir Miyajiwala, Samiksha Jagadale, Rekha Kulkarni, Raviraj Joshi. 320-325 [doi]
• Extractive Entity-Centric Summarization as Sentence Selection using Bi-EncodersElla Hofmann-Coyle, Mayank Kulkarni, Lingjue Xie, Mounica Maddela, Daniel Preotiuc-Pietro. 326-333 [doi]
• Towards Unsupervised Morphological Analysis of Polysynthetic LanguagesSujay Khandagale, Yoann Léveillé, Samuel Miller, Derek Pham, Ramy Eskander, Cass Lowry, Richard Compton, Judith Klavans, Maria Polinsky, Smaranda Muresan. 334-340 [doi]
• Self-Repetition in Abstractive Neural SummarizersNikita Salkar, Thomas A. Trikalinos, Byron C. Wallace, Ani Nenkova. 341-350 [doi]
• Domain Specific Sub-network for Multi-Domain Neural Machine TranslationAmr Hendy, Mohamed Abdelghaffar, Mohamed Afify, Ahmed Y. Tawfik. 351-356 [doi]
• Modeling Document-level Temporal Structures for Building Temporal Dependency GraphsPrafulla Kumar Choubey, Ruihong Huang. 357-365 [doi]
• Evaluating Pre-Trained Sentence-BERT with Class Embeddings in Active Learning for Multi-Label Text ClassificationLukas Wertz, Jasmina Bogojeska, Katsiaryna Mirylenka, Jonas Kuhn. 366-372 [doi]
• MiQA: A Benchmark for Inference on Metaphorical QuestionsIulia Comsa, Julian Eisenschlos, Srini Narayanan. 373-381 [doi]
• GCDT: A Chinese RST Treebank for Multigenre and Multilingual Discourse ParsingSiyao Peng, Yang Janet Liu, Amir Zeldes. 382-391 [doi]
• Assessing Combinational Generalization of Language Models in Biased ScenariosYanbo Fang, Zuohui Fu, Xin Dong 0010, Yongfeng Zhang, Gerard de Melo. 392-397 [doi]
• Controllable Text Simplification with Deep Reinforcement LearningDaiki Yanamoto, Tomoki Ikawa, Tomoyuki Kajiwara, Takashi Ninomiya, Satoru Uchida, Yuki Arase. 398-404 [doi]
• Vector Space Interpolation for Query ExpansionDeepanway Ghosal, Somak Aditya, Sandipan Dandapat, Monojit Choudhury. 405-410 [doi]
• SchAman: Spell-Checking Resources and Benchmark for Endangered Languages from AmazoniaArturo Oncevay, Gerardo Cardoso, Carlo Alva, César Lara Ávila, Jovita Vásquez Balarezo, Saúl Escobar Rodríguez, Delio Siticonatzi Camaiteri, Esaú Zumaeta Rojas, Didier López Francis, Juan López Bautista, Nimia Acho Rios, Remigio Zapata Cesareo, Héctor Erasmo Gómez Montoya, Roberto Zariquiey. 411-417 [doi]
• CoFE: A New Dataset of Intra-Multilingual Multi-target Stance Classification from an Online European Participatory Democracy PlatformValentin Barrière, Guillaume Jacquet, Léo Hemamou. 418-422 [doi]
• Exploring the Effects of Negation and Grammatical Tense on Bias ProbesSamia Touileb. 423-429 [doi]
• Promoting Pre-trained LM with Linguistic Features on Automatic Readability AssessmentShudi Hou, Simin Rao, Yu Xia, Sujian Li. 430-436 [doi]
• An Empirical Study of Pipeline vs. Joint approaches to Entity and Relation ExtractionZhaohui Yan, Zixia Jia, Kewei Tu. 437-443 [doi]
• CLASP: Few-Shot Cross-Lingual Data Augmentation for Semantic ParsingAndy Rosenbaum, Saleh Soltan, Wael Hamza, Marco Damonte, Isabel Groves, Amir Saffari. 444-462 [doi]
• Plug and Play Knowledge Distillation for kNN-LM with External LogitsXuyang Jin, Tao Ge, Furu Wei. 463-469 [doi]
• How Well Do Multi-hop Reading Comprehension Models Understand Date Information?Xanh Ho, Saku Sugawara, Akiko Aizawa. 470-479 [doi]
• Dodging the Data Bottleneck: Automatic Subtitling with Automatically Segmented ST CorporaSara Papi, Alina Karakanta, Matteo Negri, Marco Turchi. 480-487 [doi]
• How to tackle an emerging topic? Combining strong and weak labels for Covid news NERAleksander Ficek, Fangyu Liu 0001, Nigel Collier. 488-496 [doi]