UPDATE ON NEW PUBLICATIONS

Time for an update on recent work of the HD-NLP Group -- which includes an ICLR 2024 and a TACL publication, two main papers at ACL 2024, and papers at *SEM 2024, RATIO 2024 and SIGTYP 2024.

2024 started with new work by Frederick Riemenschneider and Kevin Krahn, who won the SIGTYP 2024 Shared Task with Enhancing Low-Resource Language Analysis With Character-Aware Hierarchical Transformers (last news update).

• Frederick Riemenschneider and Kevin Krahn: Heidelberg-Boston @ SIGTYP 2024 Shared Task: Enhancing Low-Resource Language Analysis With Character-Aware Hierarchical Transformers Proc. of the 6th Workshop on Research in Computational Linguistic Typology and Multilingual NLP

and a collaboration across the Universities of Koç, Hacettepe, Heidelberg & Pisa, Amsterdam, Utrecht & Malta to develop VILMA, a new benchmark that helps answer the question how well video-language models can process spatio-temporal events, presented at ICLR 2024 in Vienna. See here for an overview.

• Ilker Kesen, Andrea Pedrotti, Mustafa Dogan, Michele Cafagna, Emre Can Acikgoz, Letitia Parcalabescu, Iacer Calixto, Anette Frank, Albert Gatt, Aykut Erdem, Erkut Erdem: ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models, ICLR 2024

Next, we are happy to report on two papers by Xiyan Fu on Compositional Generalization: One appearing in TACL, to be presented at ACL 2024 about Compositional Generalization in NLI in a Continual Learning setting, another one on Compositional Structured Explanation Generation with Dynamic Modularized Reasoning, to be presented in the upcoming *SEM Conference at NAACL 2024.

• Xiyan Fu & Anette Frank: Exploring Continual Learning of Compositional Generalization in NLI, to appear in Transactions of the Association of Computational Linguistics (TACL).

• Xiyan Fu & Anette Frank: Compositional Structured Explanation Generation with Dynamic Modularized Reasoning, to be presented at *SEM 2024, the 13th Joint Conference on Lexical and Computational Semantics, co-located with NAACL.

Our project ACCEPT will present our recent work in the 1st International Conference on Recent Advances in Robust Argumentation Machines (RATIO-24):

• Moritz Plenz, Philipp Heinisch, Anette Frank and Philipp Cimiano: PAKT: Perspectivized Argumentation Knowledge Graph and Tool for Deliberation Analysis, in: Proceedings of the 1st International Conference on Recent Advances in Robust Argumentation Machines (RATIO-24), LNCS, Springer.

Last but not least, two long papers will appear in the ACL 2024 main conference in Bangkok: one first-authored by Letitia Parcalabescu, one by Moritz Plenz:

• Letitia Parcalabescu and Anette Frank: On Measuring Faithfulness or Self-consistency of Natural Language Explanations. Proc. of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024).

• Moritz Plenz and Anette Frank: Graph Language Models. Proc. of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024).

Congratulations to all authors!