@inproceedings{salonen:20004:sign-lang:lrec, author = {Salonen, Juhana and Kronqvist, Antti and Jantunen, Tommi}, title = {The Corpus of {Finnish} {Sign} {Language}}, pages = {197--202}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2020} 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/20004.html}, abstract = {This paper presents the Corpus of Finnish Sign Language (Corpus FinSL), a structured and annotated collection of Finnish Sign Language (FinSL) videos published in May 2019 in FIN-CLARIN's Language Bank of Finland. The corpus is divided into two subcorpora, one of which comprises elicited narratives and the other conversations. All of the FinSL material has been annotated using ELAN and the lexical database Finnish Signbank. Basic annotation includes ID-glosses and translations into Finnish. The anonymized metadata of Corpus FinSL has been organized in accordance with the IMDI standard. Altogether, Corpus FinSL contains nearly 15 hours of video material from 21 FinSL users. Corpus FinSL has already been exploited in FinSL research and teaching, and it is predicted that in the future it will have a significant positive impact on these fields as well as on the status of the sign language community in Finland.} } @inproceedings{cassidy-etal-2018-signbank:lrec, author = {Cassidy, Steve and Crasborn, Onno and Nieminen, Henri and Stoop, Wessel and Hulsbosch, Micha and Even, Susan and Komen, Erwin and Johnston, Trevor}, title = {{S}ignbank: Software to Support Web Based Dictionaries of Sign Language}, pages = {2359--2364}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Hasida, Koiti and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios and Tokunaga, Takenobu}, booktitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {7--12}, month = may, year = {2018}, isbn = {979-10-95546-00-9}, language = {english}, url = {https://aclanthology.org/L18-1374} } @inproceedings{jantunen:16006:sign-lang:lrec, author = {Jantunen, Tommi and Pippuri, Outi and Wainio, Tuija and Puupponen, Anna and Laaksonen, Jorma}, title = {Annotated video corpus on {FinSL} with {Kinect} and computer-vision data}, pages = {93--100}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining}, maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {28}, month = may, year = {2016}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/16006.html}, abstract = {This paper presents an annotated video corpus of Finnish Sign Language (FinSL) to which has been appended Kinect and computer-vision data. The video material consists of signed retellings of the stories Snowman and Frog, where are you?, elicited from 12 native FinSL signers in a dialogue setting. The recordings were carried out with 6 cameras directed toward the signers from different angles, and 6 signers were also recorded with one Kinect motion and depth sensing input device. All the material has been annotated in ELAN for signs, translations, grammar and prosody. To further facilitate research into FinSL prosody, computer-vision data describing the head movements and the aperture changes of the eyes and mouth of all the signers has been added to the corpus. The total duration of the material is 45 minutes and that part of it that is permitted by research consents is available for research purposes via the LAT online service of the Language Bank of Finland. The paper briefly demonstrates the linguistic use of the corpus.} } @inproceedings{keranen:16016:sign-lang:lrec, author = {Ker{\"a}nen, Jarkko and Syrj{\"a}l{\"a}, Henna and Salonen, Juhana and Takkinen, Ritva}, title = {The Usability of the Annotation}, pages = {111--116}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining}, maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {28}, month = may, year = {2016}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/16016.html}, abstract = {Several corpus projects for sign languages have tried to establish conventions and standards for the annotation of signed data. When discussing corpora, it is necessary to develop a way of considering and evaluating holistically the features and problems of annotation. This paper aims to develop a conceptual framework for the evaluation of the usability of annotations. The purpose of the framework is not to give conventions for annotating but to offer tools for the evaluation of the usability of the annotation, in order to make annotations more usable and make it possible to justify and explain decisions about annotation conventions. Based on our experience of annotation in the corpus project of Finland`s Sign Languages (CFINSL), we have developed six principles for the evaluation of annotation. In this article, using these six principles, we evaluate the usability of the annotations in CFINSL and other corpus projects. The principles have offered benefits in CFINSL: we are able to evaluate our annotations more systematically and holistically than ever before. Our work can be seen as an effort to bring a framework of usability to corpus work.} } @inproceedings{salonen:16017:sign-lang:lrec, author = {Salonen, Juhana and Takkinen, Ritva and Puupponen, Anna and Nieminen, Henri and Pippuri, Outi}, title = {Creating Corpora of {Finland}'s Sign Languages}, pages = {179--184}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining}, maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {28}, month = may, year = {2016}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/16017.html}, abstract = {This paper discusses the process of creating corpora of the sign languages used in Finland, Finnish Sign Language (FinSL) and Finland-Swedish Sign Language (FinSSL). It describes the process of getting informants and data, editing and storing the data, the general principles of annotation, and the creation of a web-based lexical database, the FinSL Signbank, developed on the basis of the NGT Signbank, which is a branch of the Auslan Signbank. The corpus project of Finland{\' }s Sign Languages (CFINSL) started in 2014 at the Sign Language Centre of the University of Jyv{\"a}skyl{\"a}. Its aim is to collect conversations and narrations from 80 FinSL users and 20 FinSSL users who are living in different parts of Finland. The participants are filmed in signing sessions led by a native signer in the Audio-visual Research Centre at the University of Jyv{\"a}skyl{\"a}. The edited material is stored in the IDA storage service produced by the CSC -- IT Center for Science, and the metadata will be saved into CMDI metadata. Every informant is asked to sign a consent form where they state for what kinds of purposes their signing can be used. The corpus data are annotated using the ELAN tool. At the moment, annotations are created on the levels of glosses and translation.} }