IMS is delighted to announce a series of news publications at EMNLP and CoNLL with IMS researchers and collaborators:
Proceedings of EMNLP. Singapore, 2023:
- An Attribution Method for Siamese Encoders.
Lucas Möller, Dmitry Nikolaev and Sebastian Padó. - Multilingual estimation of political-party positioning: From label aggregation to long-input Transformers.
Dmitry Nikolaev, Tanise Ceron and Sebastian Padó. - To Split or Not to Split: Composing Compounds in Contextual Vector Spaces
Chris Jenkins; Filip Miletic; Sabine Schulte im Walde. - Understanding Computational Models of Semantic Change: New Insights from the Speech Community.
Filip Miletic, Anne Przewozny-Desriaux, Ludovic Tanguy.
Findings of EMNLP. Singapore, 2023:
- Improving Cross-lingual Transfer through Subtree-aware Word Reordering.
Ofir Arviv, Dmitry Nikolaev, Taelin Karidi, and Omri Abend. - Data Augmentation Techniques for Machine Translation of Code Switched Texts: A Comparative Study.
Injy Hamed, Nizar Habash, Ngoc Thang Vu.
Proceedings of the BlackboxNLP workshop. Singapore, 2023:
- Investigating semantic subspaces of Transformer sentence embeddings through linear structural probing.
Dmitry Nikolaev and Sebastian Padó.
Proceedings of the Big Picture Workshop: Crafting a Research Narrative, Singapore, 2023:
- Bridging emotion role labeling and appraisal-based emotion analysis.
Roman Klinger.
Proceedings of CoNLL. Singapore, 2023:
- Investigating the Nature of Disagreements on Mid-Scale Ratings: A Case Study on the Abstractness-Concreteness Continuum.
Urban Knuples, Diego Frassinelli, Sabine Schulte im Walde. - HNC: Leveraging Hard Negative Captions towards Models with Fine-Grained Visual-Linguistic Comprehension Capabilities.
Esra Dönmez*, Pascal Tilli*, Hsiu-Yu Yang*, Ngoc Thang Vu and Carina Silberer.