@inproceedings{yazdani-etal-2026-critical:lrec,
  author    = {Yazdani, Shakib and Hamidullah, Yasser and Espa{\~n}a-Bonet, Cristina and Avramidis, Eleftherios and van Genabith, Josef},
  title     = {A Critical Study of Automatic Evaluation in Sign Language Translation},
  pages     = {9535--9548},
  editor    = {Piperidis, Stelios and Bel, N{\'u}ria and van den Heuvel, Henk and Ide, Nancy and Krek, Simon and Toral, Antonio},
  booktitle = {15th International Conference on Language Resources and Evaluation ({LREC} 2026)},
  publisher = {{ELRA Language Resources Association (ELRA)}},
  address   = {Palma, Mallorca, Spain},
  day       = {11--16},
  month     = may,
  year      = {2026},
  isbn      = {978-2-493814-49-4},
  language  = {english},
  url       = {https://lrec.elra.info/lrec2026-main-749},
  doi       = {10.63317/4n2sooe4fb2i},
  abstract  = {Automatic evaluation metrics are crucial for advancing sign language translation (SLT). Current SLT evaluation metrics, such as BLEU and ROUGE, are only text-based, and it remains unclear to what extent text-based metrics can reliably capture the quality of SLT outputs. To address this gap, we investigate the limitations of text-based SLT evaluation metrics by analyzing six metrics, including BLEU, chrF, and ROUGE, as well as BLEURT on the one hand, and large language model (LLM)-based evaluators such as G-Eval and GEMBA zero-shot direct assessment on the other hand. Specifically, we assess the consistency and robustness of these metrics under three controlled conditions: paraphrasing, hallucinations in model outputs, and variations in sentence length. Our analysis highlights the limitations of lexical overlap metrics and demonstrates that while LLM-based evaluators better capture semantic equivalence often missed by conventional metrics, they can also exhibit bias toward LLM-paraphrased translations. Moreover, although all metrics are able to detect hallucinations, BLEU tends to be overly sensitive, whereas BLEURT and LLM-based evaluators are comparatively lenient toward subtle cases. This motivates the need for multimodal evaluation frameworks that extend beyond text-based metrics to enable a more holistic assessment of SLT outputs.}
}

@inproceedings{nunnari-etal-2024-fabeln:lrec,
  author    = {Nunnari, Fabrizio and Avramidis, Eleftherios and Espa{\~n}a-Bonet, Cristina and Gonz{\'a}lez, Marco and Hennes, Anna and Gebhard, Patrick},
  title     = {{DGS-Fabeln-1}: A Multi-Angle Parallel Corpus of Fairy Tales between {German} {Sign} {Language} and {German} Text},
  pages     = {4847--4857},
  editor    = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen},
  booktitle = {2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation ({LREC-COLING} 2024)},
  publisher = {{ELRA Language Resources Association (ELRA) and the International Committee on Computational Linguistics (ICCL)}},
  address   = {Torino, Italy},
  day       = {20--25},
  month     = may,
  year      = {2024},
  isbn      = {978-2-493814-10-4},
  language  = {english},
  url       = {https://aclanthology.org/2024.lrec-main.434},
  doi       = {10.63317/46w4kw3gmw3v},
  abstract  = {We present the acquisition process and the data of DGS-Fabeln-1, a parallel corpus of German text and videos containing German fairy tales interpreted into the German Sign Language (DGS) by a native DGS signer. The corpus contains 573 segments of videos with a total duration of 1 hour and 32 minutes, corresponding with 1428 written sentences. It is the first corpus of semi-naturally expressed DGS that has been filmed from 7 angles, and one of the few sign language (SL) corpora globally which have been filmed from more than 3 angles and where the listener has been simultaneously filmed. The corpus aims at aiding research at SL linguistics, SL machine translation and affective computing, and is freely available for research purposes at the following address: https://doi.org/10.5281/zenodo.10822097.}
}