Rolando Coto-Solano
COMPUTATIONAL LINGUISTICS
Interests:
Natural Language Processing for Indigenous and Under-Resourced Languages. Speech Recognition. Automated parsing. Language documentation, revitalization and technology.
Tonal phonetics and phonology, typologies of tonal reduction. Sociophonetics.
Chibchan, Otomanguean and Polynesian languages.
Email:
rolando.a.coto.solano [at] dartmouth.edu
CURRENT RESEARCH
PUBLICATIONS
NLP AND ASR IN INDIGENOUS LANGUAGES
I build automatic speech recognition (ASR) models for Indigenous languages like Cook Islands Māori (ICLDC paper), and Bribri (NAACL paper) and Cabécar from Costa Rica. I also work on parsing using Universal Dependencies (Bribri treebank paper).
COMPUTATIONAL SOCIOPHONETICS
I use forced alignment to study interisland variation in Cook Islands Māori (ICPhS paper). I have also studied workflows for the automation of sociophonetic data processing in general (LingCompass paper) and in English (Frontiers paper).
TONAL PHONETICS AND SPEECH REDUCTION
I have studied tonal reduction and its effect on spelling and the expansion of literacy in Indigenous languages (Me'phaa Vátháá reduction, Bribri reduction). I have also studied the psycholinguistics of tonal priming in Vietnamese (TAI paper).
Speech Recognition for
Indigenous Languages
Coto-Solano, R., Nicholas, S.A., Datta, S., Quint, V., Wills, P., Powell, E.N., Kokaua, L., Tanveer, S, Feldman, I. (2022). Development of automatic speech recognition for the documentation of Cook Islands Māori. Proceedings of the 13th Conference on Language Resources and Evaluation LREC 2022. Pgs. 3872-3882 (Paper).
Coto-Solano, R. (2021). Explicit Tone Transcription Improves ASR Performance in Extremely Low-Resource Languages: A Case Study in Bribri. Proceedings of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas, NAACL. DOI: 10.18653/v1/2021.americasnlp-1.20
Foley, B., Arnold, J., Coto-Solano, R., Durantin, G., Ellison, T.M., van Esch, D., Heath, S., Kratochvíl, F., Maxwell-Smith, Z., Nash, D., Olsson, O., Richards, M., San, N., Stoakes, H., Thieberger, N. & Wiles, J. (2018). Building Speech Recognition Systems for Language Documentation: The CoEDL Endangered Language Pipeline and Inference System (ELPIS). Proceedings of the 6th Workshop on Spoken Language Technologies for Under-resourced Languages. Pgs. 200-204. DOI: 10.21437/SLTU.2018-42
NLP for Indigenous Languages
Coto-Solano, R. (2022). Evaluating Word Embeddings in Extremely Under-Resourced Languages: A Case Study in Bribri. Proceedings of the 29th International Conference on Computational Linguistics. Pgs 4455-4467 (Paper)
Abteen, E., Mager, M., Oncevay, A., Chaudhary, V., Chiruzzo, L., Fan, A., Ortega, J., Ramos, R., Rios, A., Meza Ruiz, I.V., Giménez-Lugo, G., Mager, E., Neubig, G., Palmer, A., Coto-Solano, R., Vu, T. & Kann, K. (2022). AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-Resource Languages. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Pgs. 6279-6299. DOI: 10.18653/v1/2022.acl-long.435
Coto-Solano, R.; Flores-Solórzano, S. & Loáiciga, S. (2021). Towards Universal Dependencies for Bribri. Proceedings of the Fifth Workshop on Universal Dependencies, SyntaxFest 2021. Pgs 16-29. (Paper)
Mager, M., Oncevay, A., Ebrahimi, A., Ortega, J., Rios, A., Fan, A., Gutierrez-Vasques, X., Chiruzzo, L., Giménez-Lugo, G., Ramos, R., Meza Ruiz, I.V., Coto-Solano, R., Palmer, A., Mager-Hois, E., Chaudhary, V., Neubig, G., Vu, N.T., & Kann, K. (2021). Findings of the AmericasNLP 2021 Shared Task on Open Machine Translation for Indigenous Languages of the Americas. Proceedings of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas, NAACL. DOI: 10.18653/v1/2021.americasnlp-1.23
Feldman, I. & Coto-Solano, R. (2020). Neural Machine Translation Models with Back-Translation for the Extremely Low-Resource Indigenous Language Bribri. Proceedings of the 28th International Conference on Computational Linguistics (COLING) 2020. Pgs. 3965-3976. DOI: 10.18653/v1/2020.coling-main.351
Coto-Solano, R.; Nicholas, S.A. & Wray, S. (2018). Development of Natural Language Processing Tools for Cook Islands Māori. Proceedings of the 16th Annual Workshop of The Australasian Language Technology Association. Pgs. 26-33. (Paper)
Sociophonetics
Coto-Solano, R. (2022). Computational Sociophonetics Using Automatic Speech Recognition. Language and Linguistics Compass, September 2022, e12474, Pgs. 1-17. DOI: 10.1111/lnc3.12474
Coto-Solano, R., Stanford, J. & Reddy, S. (2021). Advances in completely automated vowel analysis for sociophonetics: Using end-to-end speech recognition systems with DARLA. Frontiers in Artificial Intelligence, 24 Sept 2021. DOI: 10.3389/frai.2021.662097
Coto-Solano, R., Nicholas, S.A.; Hoback, B.; & Tiburcio Cano, G. (2021). Managing data for Untrained Forced Alignment of Indigenous Languages. In: Berez-Kroeker, A. et al. (eds). The Open Handbook of Linguistic Data Management. Cambridge, MA: MIT Press. Pgs. 423-436. DOI: 10.7551/mitpress/12200.003.0040
Nicholas, S.A. & Coto-Solano, R. (2019). Glottal variation, teacher training and language revitalisation in the Cook Islands. Proceedings of the 2019 International Congress
of Phonetic Sciences (ICPhS) 2019. Pgs. 3602-3606. (Paper).
Coto-Solano, R. & Flores Solórzano, S. (2017). Comparison of Two Forced Alignment Algorithms in Aligning Bribri Speech. CLEIej Latin American Center for Computer Studies Electronic Journal, Vol. 20(1), DOI: 10.19153/cleiej.20.1.2
Coto-Solano, R. & Flores Solórzano, S. (2016). Untrained Forced Alignment for Automatic Annotation of Speech Corpora in Costa Rican Indigenous Languages. Revista Káñina 2016:XL(175-199). DOI: 10.15517/rk.v40i4.30234 (Spanish)
Tone
Coto-Solano, R. & Trần, D. (2022). Priming Effects of Tones in Visual Processing of Vietnamese. Proceedings of the 1st Intl. Conference on Tone and Intonation (TAI). Pgs. 81-87. DOI: 10.21437/TAI.2021-17
Coto-Solano, R. (2017). Tone and Literacy in the Me'phaa Vátháá Community. Doctoral Dissertation. (PDF)
Other linguistics papers
Birchfield, A. & Coto-Solano, R. (2021). "I am not that I play" The Use of Hypercorrection in the Performance of Gender by Shakespeare’s 'Breeches' Parts. Journal of Historical Sociolinguistics, vol. 7, no. 1, 2021, pp. 27-59. DOI: 10.1515/jhsl-2018-0022
Coto-Solano, R., Molina, A. & García, A. (2015). Correlative Structures in Bribri. University of British Columbia Working Papers in Linguistics, 2015. Pgs. 27-41. (Paper)
Coto-Solano, R. (2009). Reanálisis de las Cláusulas Relativas en la Lengua Bribri como un Caso de Linearización en la Teoría Minimalista “Reanalysis of Bribri Relative Clauses as a Case of Linearization in Minimalist Theory". Proceedings of the 2nd International Applied Linguistics Conference (CILAP). Pgs. 468-478. (Paper).
Metadata in
academic publishing
Coto-Solano, R., Córdoba, S. & Francke, H. 2009. Metadata Usage Tendencies in Latin American Electronic Journals. Proceedings of the 13th International Conference on Electronic Publishing. Pgs. 311-344. (Paper)
Coto-Solano, R. & Córdoba, S. 2008. Characteristics shared by the scientific electronic journals of Latin America and the Caribbean. Proceedings of the 12th International Conference on Electronic Publishing. Pgs. 187-202. (Paper)
Coto-Solano, R. & Córdoba, S. 2011. Buenas Prácticas en las Revistas Electrónicas Latinoamericanas ”Good Practices in Latin American Electronic Journals". In: Cetto, A.M. & Alonso, O. (eds). Calidad e Impacto de la Revista Iberoamericana "Quality and Impact of Iberoamerican Journals". Mexico City: UNAM. Pgs. 207-228. (Paper)
Coto-Solano, R. & Campos, D. 2010. El Proyecto Creative Commons en Costa Rica y la conformación del movimiento de cultura libre "The Creative Commons Project in Costa Rica and the Birth of the Free Culture Movement". In: Vercelli, A. (ed). Tercera Conferencia de Creative Commons en América Latina "Third Creative Commons Conference in Latin America". Buenos Aires: Bienes Comunes AC. Pgs. 65-75. (Paper)
EXPERIENCE
2019-Present
DARTMOUTH COLLEGE
Assistant Professor, Department of Linguistics. Adjunct Assistant Professor, Department of Computer Science. Affiliate Professor, Quantitative Social Science Program (QSS).
I teach classes on natural language processing, statistics for linguistics, and linguistic fieldwork.
2017-2019
VICTORIA UNIVERSITY OF WELLINGTON
Lecturer in Sociophonetics. School of Linguistics and Applied Language Studies and School of Mathematics and Statistics.
Taught classes in Sociolinguistics, Phonetics and Phonology and Applied Statistics.
2011-2016
UNIVERSITY OF ARIZONA
Graduate Research Associate. Department of Linguistics, American Indian Language Development Institute and Arizona Phonological Imaging Laboratory. I have worked on research on tonal reduction, on improvements to community-driven language surveys, and on work with the Kinect 3D sensor to track head motion in ultrasound tongue measurements.
I have taught two revitalization and technology classes in English and six in Spanish focusing on app design, translation of media and digital lexicography. I've also taught four classes about Indigenous linguistics and language surveys. I have served as an assistant in Phonology and Documentation classes, and as a linguistic consultant in the National Breath of Life Program at the Smithsonian Institution.
2005-2010
UNIVERSITY OF COSTA RICA
Latindex/UCRIndex Program Adjunct Coordinator. Evaluation of scientific journals, DSpace repository manager and Creative Commons Public Representative.
Instructor of two introduction to linguistics classes and three classes of Japanese as a Foreign Language.
EDUCATION
2016
Ph.D.
UNIVERSITY OF ARIZONA
Ph.D. in Linguistics. Major: Language Revitalization. Minor: Phonology.
2012
Master's Degree
UNIVERSITY OF ARIZONA
M.A. in Linguistics.
2006
Bachelor's Degree
UNIVERSITY OF COSTA RICA
B.Sc. Computer Sciences.
GRANTS AND HONORS
Fulbright Foreign Student Program: Funding for Master's Degree
National Science Foundation: Consultant for projects BCS-1601738 Assessing and Documenting the Vitality of Native American Languages and BCS-1321663 CAP Partnerships for Indigenous Knowledge and Digital Literacies.
Royal Society of New Zealand Te Apārangi, Marsden Fund. AI in 21-MAU-018 Development and optimisation of Te Vairanga Tuatua, a multimedia-multipurpose corpus of Cook Islands Māori
Office of the Prime Minister of Japan and United Nations University: Ship for World Youth Program (SWY) 2005
SKILLS
Programming: Python, LaTeX,
Java, C#, C++, SQL
Spanish (Native), English (near-native), Japanese (JLPT-N3), French (DELF-B1)
Stats: R, SPSS, Matlab
Psycholing: DMDX
Italian (PLIDA-B1), Mandarin (HSK-1), Portuguese (Advanced Low), Bribri
OTHER INTERESTS
OPEN ACCESS
Timely access to research makes a world of difference to researchers in the Global South. I've worked with Latindex, SCiELO and Creative Commons, and was a public representative for CC during the creation of the licenses for Costa Rica.
INDIGENOUS MAPPING
Behind common maps lie erased stories of peoples and lack of justice. I have collaborated in Indigenous mapping projects at AILDI, and I am part of the Google Earth Outreach Trainers Network.
AMATEUR ASTRONOMY
I've worked as a volunteer educator and telescope operator at the Flandrau Planetarium at the University of Arizona .