Table of Contents

• Including Facial Expressions in Contextual Embeddings for Sign Language GenerationCarla Viegas, Mert Inan, Lorna C. Quandt, Malihe Alikhani. 1-10 [doi]
• Leverage Points in Modality Shifts: Comparing Language-only and Multimodal Word RepresentationsLisa Bylinina, Denis Paperno, Alexey Tikhonov. 11-17 [doi]
• Revisiting Syntax-Based Approach in Negation Scope ResolutionAsahi Yoshida, Yoshihide Kato, Shigeki Matsubara. 18-23 [doi]
• When Truth Matters - Addressing Pragmatic Categories in Natural Language Inference (NLI) by Large Language Models (LLMs)Reto Gubelmann, Aikaterini-Lida Kalouli, Christina Niklaus, Siegfried Handschuh. 24-39 [doi]
• Analyzing Syntactic Generalization Capacity of Pre-trained Language Models on Japanese Honorific ConversionRyo Sekizawa, Hitomi Yanaka. 40-47 [doi]
• Improving Toponym Resolution with Better Candidate Generation, Transformer-based Reranking, and Two-Stage ResolutionZeyu Zhang 0002, Steven Bethard. 48-60 [doi]
• CRAPES:Cross-modal Annotation Projection for Visual Semantic Role LabelingAbhidip Bhattacharyya, Martha Palmer, Christoffer Heckman. 61-70 [doi]
• Not All Counterhate Tweets Elicit the Same Replies: A Fine-Grained AnalysisAbdullah Albanyan, Ahmed Hassan, Eduardo Blanco 0002. 71-88 [doi]
• Evaluating Factual Consistency of Texts with Semantic Role LabelingJing Fan, Dennis Aumiller, Michael Gertz 0001. 89-100 [doi]
• Language models are not naysayers: an analysis of language models on negation benchmarksThinh Hung Truong, Timothy Baldwin, Karin Verspoor, Trevor Cohn. 101-114 [doi]
• JSEEGraph: Joint Structured Event Extraction as Graph ParsingHuiling You, Lilja Øvrelid, Samia Touileb. 115-127 [doi]
• Generative Data Augmentation for Aspect Sentiment Quad Predictionan Wang, Junfeng Jiang, Youmi Ma, Ao Liu, Naoaki Okazaki. 128-140 [doi]
• Are Language Models Sensitive to Semantic Attraction? A Study on SurprisalYan Cong, Emmanuele Chersoni, Yu-Yin Hsu, Alessandro Lenci. 141-148 [doi]
• Syntax and Semantics Meet in the "Middle": Probing the Syntax-Semantics Interface of LMs Through AgentivityLindia Tjuatja, Emmy Liu, Lori S. Levin, Graham Neubig. 149-164 [doi]
• Can Pretrained Language Models Derive Correct Semantics from Corrupt Subwords under Noise?Xinzhe Li, Ming Liu, Shang Gao. 165-173 [doi]
• How Are Idioms Processed Inside Transformer Language Models?Ye Tian, Isobel James, Hye Son. 174-179 [doi]
• Is Shortest Always Best? The Role of Brevity in Logic-to-Text GenerationEduardo Calò, Jordi Levy, Albert Gatt, Kees van Deemter. 180-192 [doi]
• Seeking Clozure: Robust Hypernym extraction from BERT with Anchored PromptsChunhua Liu, Trevor Cohn, Lea Frermann. 193-206 [doi]
• LEXPLAIN: Improving Model Explanations via Lexicon SupervisionOrevaoghene Ahia, Hila Gonen, Vidhisha Balachandran, Yulia Tsvetkov, Noah A. Smith. 207-216 [doi]
• KGLM: Integrating Knowledge Graph Structure in Language Models for Link PredictionJason Youn, Ilias Tagkopoulos. 217-224 [doi]
• Probing Out-of-Distribution Robustness of Language Models with Parameter-Efficient Transfer LearningHyunsoo Cho, Choonghyun Park, Junyeob Kim, Hyuhng Joon Kim, Kang Min Yoo, Sang-goo Lee. 225-235 [doi]
• Limits for learning with language modelsNicholas Asher, Swarnadeep Bhar, Akshay Chaturvedi, Julie Hunter, Soumya Paul. 236-248 [doi]
• Does Character-level Information Always Improve DRS-based Semantic Parsing?Tomoya Kurosawa, Hitomi Yanaka. 249-258 [doi]
• Testing Paraphrase Models on Recognising Sentence Pairs at Different Degrees of Semantic OverlapQiwei Peng 0002, David J. Weir, Julie Weeds. 259-269 [doi]
• Mann" is to "Donna asis to Reine Adapting the Analogy Task for Multilingual and Contextual EmbeddingsTimothee Mickus, Eduardo Calò, Léo Jacqmin, Denis Paperno, Mathieu Constant. 270-283 [doi]
• Scalable Performance Analysis for Vision-Language ModelsSantiago Castro, Oana Ignat, Rada Mihalcea. 284-294 [doi]
• PCFG-Based Natural Language Interface Improves Generalization for Controlled Text GenerationJingyu Zhang, James R. Glass, Tianxing He. 295-313 [doi]
• True Detective: A Deep Abductive Reasoning Benchmark Undoable for GPT-3 and Challenging for GPT-4Maksym Del, Mark Fishel. 314-322 [doi]
• Guiding Zero-Shot Paraphrase Generation with Fine-Grained Control TokensTeemu Vahtola, Mathias Creutz, Jörg Tiedemann. 323-337 [doi]
• A Tale of Two Laws of Semantic Change: Predicting Synonym Changes with Distributional Semantic ModelsBastien Liétard, Mikaela Keller, Pascal Denis. 338-352 [doi]
• Semantically-informed Hierarchical Event ModelingShubhashis Roy Dipta, Mehdi Rezaee, Francis Ferraro. 353-369 [doi]
• Representation of Lexical Stylistic Features in Language Models' Embedding SpaceQing Lyu 0001, Marianna Apidianaki, Chris Callison-Burch. 370-387 [doi]
• Event Semantic Knowledge in Procedural Text UnderstandingGhazaleh Kazeminejad, Martha Palmer. 388-398 [doi]
• Leveraging Active Learning to Minimise SRL Annotation Across CorporaSkatje Myers, Martha Palmer. 399-408 [doi]
• Estimating Semantic Similarity between In-Domain and Out-of-Domain SamplesRhitabrat Pokharel, Ameeta Agrawal. 409-416 [doi]
• Query Generation Using GPT-3 for CLIP-Based Word Sense Disambiguation for Image RetrievalXiaomeng Pan, Zhousi Chen, Mamoru Komachi. 417-422 [doi]
• Functional Distributional Semantics at ScaleChun Hei Lo, Hong Cheng 0001, Wai Lam, Guy Emerson. 423-436 [doi]
• FEED PETs: Further Experimentation and Expansion on the Disambiguation of Potentially Euphemistic TermsPatrick Lee, Iyanuoluwa Shode, Alain Chirino Trujillo, Yuan Zhao, Olumide E. Ojo, Diana Cuevas Plancarte, Anna Feldman, Jing Peng 0001. 437-448 [doi]
• Monolingual Phrase Alignment as Parse Forest MappingSora Kadotani, Yuki Arase. 449-455 [doi]
• Empirical Sufficiency Lower Bounds for Language Modeling with Locally-Bootstrapped Semantic StructuresJakob Prange, Emmanuele Chersoni. 456-468 [doi]
• Probing neural language models for understanding of words of estimative probabilityDamien Sileo, Marie-Francine Moens. 469-476 [doi]
• Arithmetic-Based Pretraining Improving Numeracy of Pretrained Language ModelsDominic Petrak, Nafise Sadat Moosavi, Iryna Gurevych. 477-493 [doi]
• Robust Integration of Contextual Information for Cross-Target Stance DetectionTilman Beck, Andreas Waldis, Iryna Gurevych. 494-511 [doi]
• Adverbs, SurprisinglyDmitry Nikolaev 0003, Collin F. Baker, Miriam R. L. Petruck, Sebastian Padó. 512-526 [doi]
• Can Sequence-to-Sequence Transformers Naturally Understand Sequential Instructions?Xiang Zhou, Aditya Gupta, Shyam Upadhyay, Mohit Bansal, Manaal Faruqui. 527-534 [doi]