@inproceedings{bejarano:22013:sign-lang:lrec,
  author    = {Bejarano, Gissella and Huamani-Malca, Joe and Cerna-Herrera, Francisco and Alva-Manchego, Fernando and Rivas, Pablo},
  title     = {{PeruSIL}: A Framework to Build a Continuous {Peruvian} {Sign} {Language} Interpretation Dataset},
  pages     = {1--8},
  editor    = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Schulder, Marc},
  booktitle = {Proceedings of the {LREC2022} 10th Workshop on the Representation and Processing of Sign Languages: Multilingual Sign Language Resources},
  maintitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)},
  publisher = {{European Language Resources Association (ELRA)}},
  address   = {Marseille, France},
  day       = {25},
  month     = jun,
  year      = {2022},
  isbn      = {979-10-95546-86-3},
  language  = {english},
  url       = {https://www.sign-lang.uni-hamburg.de/lrec/pub/22013.html},
  abstract  = {Video-based datasets for Continuous Sign Language are scarce due to the challenging task of recording videos from native signers and the reduced number of people who can annotate sign language. COVID-19 has evidenced the key role of sign language interpreters in delivering nationwide health messages to deaf communities. In this paper, we present a framework for creating a multi-modal sign language interpretation dataset based on videos and we use it to create the first dataset for Peruvian Sign Language (LSP) interpretation annotated by hearing volunteers who have intermediate knowledge of PSL guided by the video audio. We rely on hearing people to produce a first version of the annotations, which should be reviewed by native signers in the future. Our contributions: i) we design a framework to annotate a sign Language dataset; ii) we release the first annotated LSP multi-modal interpretation dataset (AEC); iii) we evaluate the annotation done by hearing people by training a sign language recognition model. Our model reaches up to 80.3{\%} of accuracy among a minimum of five classes (signs) AEC dataset, and 52.4{\%} in a second dataset. Nevertheless, analysis by subject in the second dataset show variations worth to discuss.}
}

@inproceedings{huamani-malca-etal-2024-lessons:lrec,
  author    = {Huamani-Malca, Joe and Rodr{\'i}guez Mondo{\~n}edo, Miguel and Cerna-Herrera, Francisco and Bejarano, Gissella and V{\'a}squez Roque, Carlos and Ramos Cantu, Cesar Augusto and Oporto P{\'e}rez, Sabina},
  title     = {Lessons from Deploying the First Bilingual Peruvian Sign Language - Spanish Online Dictionary},
  pages     = {10316--10323},
  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.901},
  abstract  = {Bilingual dictionaries present several challenges, especially for sign languages and oral languages, where multimodality plays a role. We deployed and tested the first bilingual Peruvian Sign Language (LSP) - Spanish Online Dictionary. The first feature allows the user to introduce a text and receive as a result a list of videos whose glosses are related to the input text or Spanish word. The second feature allows the user to sign in front of the camera and shows the five most probable Spanish translations based on the similarity between the input sign and gloss-labeled sign videos used to train a machine learning model. These features are constructed in a design and architecture that differentiates among the coincidence for the Spanish text searched, the sign gloss, and Spanish translation. We explain in depth how these concepts or database columns impact the search. Similarly, we share the challenges of deploying a real-world machine learning model for isolated sign language recognition through Amazon Web Services (AWS).}
}