Update papers.bib

Author: verenablaschke

_bibliography/papers.bib

@@ -1,5 +1,18 @@
 ---
 ---
+
+@inproceedings{blaschke-etal-2025-multi,
+      title={A Multi-Dialectal Dataset for {German} Dialect {ASR} and Dialect-to-Standard Speech Translation},
+      author={Blaschke, Verena and Winkler, Miriam and Förster, Constantin and Wenger-Glemser, Gabriele and Plank, Barbara},
+      abstract={Although Germany has a diverse landscape of dialects, they are underrepresented in current automatic speech recognition (ASR) research. To enable studies of how robust models are towards dialectal variation, we present Betthupferl, an evaluation dataset containing four hours of read speech in three dialect groups spoken in Southeast Germany (Franconian, Bavarian, Alemannic), and half an hour of Standard German speech. We provide both dialectal and Standard German transcriptions, and analyze the linguistic differences between them. We benchmark several multilingual state-of-the-art ASR models on speech translation into Standard German, and find differences between how much the output resembles the dialectal vs. standardized transcriptions. Qualitative error analyses of the best ASR model reveal that it sometimes normalizes grammatical differences, but often stays closer to the dialectal constructions.},
+      booktitle = {Interspeech 2025},
+      pages     = {913--917},
+      doi       = {10.21437/Interspeech.2025-318},
+      url={https://www.isca-archive.org/interspeech_2025/blaschke25_interspeech.html},
+      year = 2025,
+      month = aug,
+}
+
 @inproceedings{ma-etal-2025-algorithmic,
     title = "Algorithmic Fidelity of Large Language Models in Generating Synthetic {G}erman Public Opinions: A Case Study",
     author = "Ma, Bolei  and
@@ -206,6 +219,39 @@ @inproceedings{sauberli-etal-2025-llms
     abstract = "Knowing how test takers answer items in educational assessments is essential for test development, to evaluate item quality, and to improve test validity. However, this process usually requires extensive pilot studies with human participants. If large language models (LLMs) exhibit human-like response behavior to test items, this could open up the possibility of using them as pilot participants to accelerate test development. In this paper, we evaluate the human-likeness or psychometric plausibility of responses from 18 instruction-tuned LLMs with two publicly available datasets of multiple-choice test items across three subjects: reading, U.S. history, and economics. Our methodology builds on two theoretical frameworks from psychometrics which are commonly used in educational assessment, classical test theory and item response theory. The results show that while larger models are excessively confident, their response distributions can be more human-like when calibrated with temperature scaling. In addition, we find that LLMs tend to correlate better with humans in reading comprehension items compared to other subjects. However, the correlations are not very strong overall, indicating that LLMs should not be used for piloting educational assessments in a zero-shot setting."
 }
 
+@inproceedings{blaschke-etal-2025-analyzing,
+    title = "Analyzing the Effect of Linguistic Similarity on Cross-Lingual Transfer: Tasks and Experimental Setups Matter",
+    author = "Blaschke, Verena  and
+      Fedzechkina, Masha  and
+      Ter Hoeve, Maartje",
+    editor = "Che, Wanxiang  and
+      Nabende, Joyce  and
+      Shutova, Ekaterina  and
+      Pilehvar, Mohammad Taher",
+    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
+    month = jul,
+    year = "2025",
+    address = "Vienna, Austria",
+    publisher = "Association for Computational Linguistics",
+    url = "https://aclanthology.org/2025.findings-acl.454/",
+    doi = "10.18653/v1/2025.findings-acl.454",
+    pages = "8653--8684",
+    ISBN = "979-8-89176-256-5",
+    abstract = "Cross-lingual transfer is a popular approach to increase the amount of training data for NLP tasks in a low-resource context. However, the best strategy to decide which cross-lingual data to include is unclear. Prior research often focuses on a small set of languages from a few language families and/or a single task. It is still an open question how these findings extend to a wider variety of languages and tasks. In this work, we analyze cross-lingual transfer for 263 languages from a wide variety of language families. Moreover, we include three popular NLP tasks: POS tagging, dependency parsing, and topic classification. Our findings indicate that the effect of linguistic similarity on transfer performance depends on a range of factors: the NLP task, the (mono- or multilingual) input representations, and the definition of linguistic similarity."
+}
+
+@incollection{nerbonne-etal-2025-methods,
+  title = {Methods and Resources in {Germanic} Variationist Linguistics},
+  author = {Nerbonne, John and Blaschke, Verena and Sch\"{u}tze, Hinrich and Plank, Barbara},
+  booktitle = {Oxford Research Encyclopedia of Linguistics},
+  publisher = {Oxford University Press},
+  editor = {K\"{u}rschner, Sebastian and Dammel, Antje},
+  doi = {10.1093/acrefore/9780199384655.013.1033},
+  url = {https://doi.org/10.1093/acrefore/9780199384655.013.1033},
+  year = {2025},
+  month = may,
+}
+
 @inproceedings{shim-plank-2025-dialetto,
     title = "Dialetto, ma Quanto Dialetto? Transcribing and Evaluating Dialects on a Continuum",
     author = "Shim, Ryan Soh-Eun  and