Daniel Hershcovich
University of Copenhagen
compositional generalization
semantics
ucca
meaning representation
amr
legal reasoning
semantic parsing
logical reasoning
meaning representations
evaluation
pragmatics
language models
parsing
natural language processing
cross-lingual transfer
22
presentations
4
number of views
SHORT BIO
Daniel Hershcovich is a Tenure-Track Assistant Professor at the NLP section, Department of Computer Science, University of Copenhagen, Denmark. He did his PhD at the Hebrew University of Jerusalem with Ari Rappoport and Omri Abend on meaning representation parsing. During 2008-2019, Daniel was also at Project Debater, IBM Research. His research interests include cross-cultural and cross-lingual adaptation of (and investigation with) NLP models, interpretable representation of natural language syntax, semantics and pragmatics, and promoting welfare, sustainability and responsible behavior through language technology.
Presentations
Probing for Hyperbole in Pre-Trained Language Models
Nina Schneidermann and 2 other authors
What does the Failure to Reason with "Respectively'' in Zero/Few-Shot Settings Tell Us about Language Models?
Ruixiang Cui and 3 other authors
On Evaluating Multilingual Compositional Generalization with Translated Datasets
Daniel Hershcovich and 1 other author
What's the Meaning of Superhuman Performance in Today's NLU?
Simone Tedeschi and 11 other authors
Cross-Cultural Transfer Learning for Chinese Offensive Language Detection
Li Zhou and 3 other authors
Towards Climate Awareness in NLP Research
Daniel Hershcovich
Compositional Generalization in Multilingual Semantic Parsing over Wikidata
Ruixiang Cui and 3 other authors
Can AMR Assist Legal and Logical Reasoning?
Nikolaus Schrack and 3 other authors
A Dataset of Sustainable Diet Arguments on Twitter
Daniel Hershcovich
Evaluating Deep Taylor Decomposition for Reliability Assessment in the Wild
Stephanie Brandl and 2 other authors
Challenges and Strategies in Cross-Cultural NLP
Daniel Hershcovich and 13 other authors
Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color
Mostafa Abdou and 5 other authors
A Multilingual Benchmark for Probing Negation-Awareness with Minimal Pairs
Mareike Hartmann and 6 other authors
Great Service! Fine-grained Parsing of Implicit Arguments
Ruixiang Cui and 1 other author
Meaning Representation of Numeric Fused-Heads in UCCA
Ruixiang Cui and 1 other author
Parsing, Evaluation and Applications
Daniel Hershcovich