Henkilökohtainen profiili
Tutkimuskohteet
My interests have spun off from many years of research in Natural Language Processing (NLP) to Sustainability and Optimization. They can be characterized by the triangle:
Dialogue - Health - Optimization
I. Dialogue
By engaging in dialogue people can get help and solve real-world problems related to most of the 17 Goals of the UN, including
- NO POVERTY (#1),
- ZERO HUNGER (#2),
- GOOD HEALTH AND WELL-BEING (#3),
- QUALITY EDUCATION (#4),
- REDUCED INEQUALITIES (#10), and
- SUSTAINABLE CITIES AND COMMUNITIES (#11).
In NLP, dialogue is approached through
- Representations of understanding, meaning, and semantics, such as graph-based and Transformer-based text encodings
- Dialogue language models, such as Chat GPT-3, and planning
- Gathering and developing resources for indigenous languages, and their speakers.
To process meaning and dialogue, I have worked on linear-time transducers (e.g., FS Transducers) and linear-space transducers (e.g., Transformer, and Constraint Grammar), and to develop resources, I worked on the parallel Bible alignment (HELFI corpus) and the researcher services of the Language Bank of Finland at CSC.
II. Health
Health is itself one of the UN goals, but also connected to other goals:
- SUSTAINABLE CITIES AND COMMUNITIES (#11),
- AFFORDABLE AND CLEAN ENERGY (#7),
- CLIMATE ACTION (#12), and
- LIFE BELOW WATER (#15), and ON LAND (#16),
all of which are indirectly researched at UH's Hyytiälä Research Station in Juupajoki. In 2020-2021, I helped to build the Hyytiälä Living Lab, a forthcoming research facility that includes sensors for Indoor Air Quality, Structure Health Monitoring, and Biometric Responses. The Lab has been designed to provide Mass Spectrometry of indoor air of the rooms, IoT Sensors, and controllable aspects of the relevant Building Technology.
III. Optimization
Optimization of resources such as energy, personnel, parts, and time are crucial for
- ZERO HUNGER (#2),
- DECENT WORK AND ECONOMIC GROWTH (#9),
- REDUCED INEQUALITIES (#10),
- SUSTAINABLE CITIES AND COMMUNITIES (#11),
- CLIMATE ACTION (#12).
I am currently working on the Academy of Finland's AI-ROT Project (at Tampere University) to develop optimization techniques for scheduling and planning. My technology palette involves Non-Monotonic Reasoning, Dynamic Programming, and other AI techniques.
In the future, I am looking for ways to combine dialogue, health and optimization, and to extend my experience to further industrial applications.
IV. Low Priority Interests
Lastly, everyone needs a less useful, purely intellectual interest. To me, it is mathematical logic: Before I started as a non-NLP-related postdoc in Nonmonotonic Logic in 2022, I started endeavouring a secondary Ph.D. in Mathematics, in particular on the mathematical foundations of Dependency Linguistics. This book would extend my previous work on Finite-State Transducer Technology, and on the linear encoding of bounded-rope-thickness (BRT) labeled graphs to an efficient implementation of Monadic Second-Order (MSO) Logic over the BRT dependency trees and BRT graph-based meaning representations used in NLP today. Such logic can also be extended to capture BRT properties and transductions of autosegmental representations of tonal morphology of some Bantu languages spoken in Africa.
However, due to the lack of funding and an industrial partner, I have been forced to postpone this endeavor to the indefinite future. If you think this topic would deserve more attention, please let me know.
Tutkimuksen ja opetuksen kuvaus
My full-time research in Language Technology is on hold, but I continue following the advances in NLP and supervising PhDs according to my Docent Contract with the Faculty.
Previously, I have taught in different faculties, international contexts, and at my alma mater. Examples:
- Automata Theory/Formal Languages (Tampere University, Spring 2023)
- Weighted Automata (TU Darmstadt: TUCaN-Modulnummer: 20-00-0782, 2014-2015)
- Artificial Intelligence II (Cambridge University, specialist supervisor for a homework group, 2014)
- 401076 Theory of Finite-State Based Parsing (clt370), 2010, 2011
- 40476Muu kieliteknologinen osio (CLT310): Contextual Formalisms and Related Logics for Automata Based Natural Language Processing, 2008
- Introduction to Linguistic Data Processing, 1993
In 2012-2013, I served as the Head of Subject (Language Technology), teaching several other courses such as:
- 401079 Seminaari (CLT340, 2012-2013)
- 401066 Proseminaari (CLT240, 2012-2013)
- 406373 Kielen morfologian käsittelyn työkalut 1 (CLT261, 2012)
- 406374 Kielen morfologian käsittelyn työkalut 2 (CLT271, 2013)
- 406251Kieliteknologian johdantokurssi (CLT140, 2012)
- 406375Tulosten esittäminen ja niiden arviointi tilastomenetelmillä (CLT255, 2012)
I am a Qualified Teacher.
Koulutustiedot
- Doctoral Student in Computing and Electrical Engineering, Tampere University, 2021-
- Teacher's Qualification (University Pedagogics), University of Helsinki, 2006-2014
- Title of Docent, Language Technology, University of Helsinki, Finland, 2006
- PhD in Language Technology, University of Helsinki, Finland, 13/9/2005
- Secondary Laudatur in Computer Science, University of Helsinki, Finland, 2005
- MA in Computational Linguistics, University of Helsinki, Finland, 1997
Ansioluettelo
Current Positions
- Postdoctoral Researcher, (AI-ROT Project), Faculty of Information Technology and Communication Sciences, Tampere University, 2022-
- Docent Contract, Department of Digital Humanities, University of Helsinki, 2021-
Previous Positions
- Postdoctoral Researcher, (AI-ROT Project), Faculty of Information Technology and Communication Sciences, Tampere University, 2022-
- Research Coordinator (Hyytiälä Living Lab), Faculty of Agriculture and Forestry, University of Helsinki, 2020-2021
- Academy Research Fellow 2013 - 2019
- Deputy Professor of Language Technology, University of Helsinki, 8/2012 – 7/2013
- University Researcher, University of Helsinki, 2008 – 2012
- Application Specialist, CSC - IT Centre for Science, Finland, 1998 – 2008
- PhD Student in Language Technology (on leave from CSC), U. Helsinki, Finland, 2002 – 2004
- Research Adjunct in Computational Linguistics, University of Helsinki, Finland, 1997 – 1998
- System Analyst, Bible Encyclopedia Publ. (Raamatun Tietokirja/AikaMedia), Finland, 1992 – 1997
Fellowships
- Visiting Scholar (total 2 months) at the Hebrew University of Jerusalem, Israel, 2018-2020
- Visiting Scholar (2 months) at the Inf. Sciences Institute, U. Southern California, USA, 2017
- Academy Research Fellow, Academy of Finland, Finland, 2013 – 2018
- Visiting Professor (1 week) at teh Inf.Sc.Dept., U. Stellenbosch, South Africa, 2013
- Visiting Fellow (1 year), Clare Hall college, University of Cambridge, UK , 2013 – 2014
- Acad.Visitor (1 year) at the Machine Intelligence Lab., Dept.Eng., Univ. Cambridge, 2013 – 2014
- Visiting Professor (2 weeks) at the Inst. Kiswahili Studies, Dar es Salaam, Tanzania, 2012
- Postdoc Research Fellow, Academy of Finland, Finland, 2009 – 2011
- Visiting Fellow (2 weeks) at the School of Mathematics, Georgia Technical U., USA, 2008
- Postdoc Fellow (2 months) at the Budapest U. Technology and Economics, Hungary, 2007
- PhD Scholarship, Nordic Academy of Advanced Study, Norway, 2002 – 2004
Participation of Supervision of Graduate Students and Postdoc Fellows
- Razie Ehsani (Visiting PostGrad/PostDoc, IşıkU), Finite-State Translation of Azerbaijani (advisor), 2018
- Uliana Petrunina (Visiting PostGrad, UTromsø), Weighted Disamb. of Russian Participles (co-advisor), 2/2018 – now
- Jack Rueter (Post Doc, UH), UniversalDependency Syntax for Erzya (PI), 2017
- Aarne Talma (PostGrad, UH), Deep Learning and Natural Language Inference (co-advisor), 2018 – now
- Josi Purhonen (Master Student, UH), Synchronization of Morph. Analysed Editions of the Hebrew and Greek Bible, 2018–now
- Miikka Silfverberg (PostGrad) (co-advisor) 2008–2016
- 4 Masters students, UH, 2008–2016
- Helsinki Language Technology Group (co-advisor), 2017–
- Helsinki FST Technology Group, UH (co-advisor), 2008 –2013
Teaching Activities
- Qualification, University Pedagogics (60 cr), University of Helsinki, Finland, 2015
- ”Qualified for the associate professorship”, DTU Compute, Danmark, 2014
- International Teaching at U. Cambridge (UK) and T.U. Darmstadt (Germany), 2013 – 2014
- Pre-Conference Tutorial presenter, ACL 2014, Bulgaria, 2013
- Deputy Professor in Lang.Technology, Dept.Modern Languages, U.Helsinki, Finland, 2012 – 2013
- Local courses in Language Technology, U.Helsinki, Finland, 1994 – 14 different
Organisation of International Scientific Meetings
- PC Co-chair of TWOLDAY 2005, FSMNLP 2008, FSMNLP 2009
- OC Chair of FSMNLP 2005
Institutional Responsibilities
- Debuty Head of Language Technology (2012–2013), U.Helsinki, Finland
- Board member of the Department of General Linguistics (1998 – 1999), U.Helsinki, Finland
Commissions of Trust
- Board Member of the Finnish Artificial Intelligence Society
- Treasurer (2020-), SIGFSM, Assoc. for Comp. Linguistics, USA
- Advisory Board member (2012–), SIGFSM, Assoc. for Comp. Linguistics, USA
- Co-applicant (nominated), Proposal for a Dagstuhl Perspectives Workshop, Germany
- Co-founder (1997), Calfat Oy, Finland
- Consultant member (2008–), Wycliffe Bible Translators, Finland
- Coordinator of the Language Bank of Finland (2005 – 2007), CSC - IT Centre for Science, Finland
- Evaluator for a Lecturer Position, UK
- Founder and President of SIGFSM (2009–2012), Assoc. for Comp. Linguistics, USA
- Guest Editor (for journals) Cambridge U.Press, Springer, CSLI Publications, IOS Press
- Program Committee member with reviewing duties, premium venues in Comp.Sc. and Comp.Linguistics (selected): ACL 2012–2017, FSMNLP 2005–2017, SCiL 2018, IJCNLP 2013–2017, Swedish LT Confer- ence 2017, Math. of Language 2017/2015/2013; IWCLUL 2015; Human Lang. Technology 2012; Empirical Methods in NLP 2014, FormalGrammar 2007/2006; Recent Advances in NLP 2011, NoDaLiDa 2007.
- Referee (proposals): Nat.Res.Found. (S.Africa), E.Aaltonen F., Wihuri F., Kone F., O. Öflund F. (Finland), Riksbankens Jubileumsfond (Sweden), Lang.Bank of Finland; Finnish Nat. Electronic Library (Finland)
- Referee (for journals): Natural Language Engineering (Cambridge), J. Logic and Computation (Oxford), Oxford Handbook of Comp.Linguistics (Oxford), J.Lang.Modeling (OASPA), Int.J.Foundations Comp.Sci. (World Scientific), SKY Journal (The Ling.Assoc.of Finland), Nordic J. African Languages (U. Helsinki), CSLI Studies in Comp.Linguistics ONLINE (CSLI Publications), Lang. Res. and Evaluation (Springer)
- Standardisation Committee member (IEC JTC1/SC2/WG2 2006 – 2007), ISO
- Supervisor Pool member (2008–) of the LANGNET Graduate School, Finland
Membership in Scientific Societies, Networks and Associations
- PI Board Member of BAULT - a multidisciplinary research community at the University of Helsinki (2010–) •
- PI Member of the HLG Community, the Helsinki Logic Group (2010–)
- Member of the Association of Computational Linguistics (ACL)
- Northern European Association for Language Technology (NEALT)
- Member of ACL Special Interest Group on Finite-State Methods (SIGFSM)
Koulutus / tieteellinen pätevyys
pedagogia, Opetustoimen henkilöstön kelpoisuus, Yliopistopedagogiikan aineopinnot, Helsingin ylipisto
2011 → 2014
Myöntöpäivä: 24 kesäk. 2015
kieliteknologia, FT, Contributions to the Theory of Finite-State Based Linguistic Grammars, Helsingin yliopisto
1998 → 13 syysk. 2005
Myöntöpäivä: 13 syysk. 2005
Tieteenalat
- 6121 Kielitieteet
- computational linguistics
- parsing
- morphology
- syntax
- statistical machine translation
- research infrastructures
- dependency syntax
- tonology
- translation alignment
- manual bitext alignment
- 113 Tietojenkäsittely- ja informaatiotieteet
- finite automata
- parsing technology
- algorithms
- coding theory
- enumerative graph theory
- finite models
- grammar inference
- 111 Matematiikka
- mathematical logic
- descriptive complexity
- aperiodic languages
Yhteistyöt ja huippututkimusalueet viimeisiltä viideltä vuodelta
Tutkimustuotos
-
Hierarchical Bracketing Encodings for Dependency Parsing as Tagging
Ezquerro, A., Vilares, D., Yli-Jyrä, A. & Gómez-Rodríguez, C., heinäk. 2025, Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Che, W., Nabende, J., Shutova, E. & Taher Pilehvar , M. (toim.). Kerrville: Association for Computational Linguistics (ACL), Vuosikerta 1. s. 18436-18450 15 Sivumäärä (Proceedings of the Annual Meeting of the Association for Computational Linguistics ).Julkaisun otsikon käännös :Hierakkinen sulutuskoodaus dependenssijäsentämisen suorittamiseksi täggaamalla Tutkimustuotos: Artikkeli kirjassa/raportissa/konferenssijulkaisussa › Konferenssiartikkeli › Tieteellinen › vertaisarvioitu
Open accessTiedosto -
Federated use of hygrothermal monitoring data in mass timber buildings: opportunities and challenges
Riggio, M., Vcelak, J., Kaitaniemi, P., Barbosa, A., Hrovatin, N., Sandak, A., Sandak, J., Mrissa, M., Kresz, M., Yli-Jyrä, A., Toivonen, R. & Alakukku, L., 2023, World Conference on Timber Engineering (WCTE 2023): Timber for a Livable Future. Nyrud, A. Q. & Malo, K. A. (toim.). Oslo: World Conference on Timber Engineering , s. 3896-3904Tutkimustuotos: Artikkeli kirjassa/raportissa/konferenssijulkaisussa › Konferenssiartikkeli › Tieteellinen › vertaisarvioitu
Open accessTiedosto -
A Derivational Model of Discontinuous Parsing
Nederhof, M.-J. & Yli-Jyrä, A., 12 heinäk. 2021, julkaisussa: Information and Computation. 279, 104619.Julkaisun otsikon käännös :Epäjatkuvan jäsentämisen derivatiivinen malli Tutkimustuotos: Artikkelijulkaisu › Artikkeli › Tieteellinen › vertaisarvioitu
-
HELFI: a Hebrew-Greek-Finnish Parallel Bible Corpus with Cross-Lingual Morpheme Alignment
Yli-Jyrä, A., Purhonen, J., Liljeqvist, M., Antturi, A., Nieminen, P., Räntilä, K. M. & Luoto, V., toukok. 2020, Proceedings of the 12th Language Resources and Evaluation Conference. Calzolari [et al.], N. (toim.). Paris: European Language Resources Association (ELRA), s. 4229–4236 8 SivumääräTutkimustuotos: Artikkeli kirjassa/raportissa/konferenssijulkaisussa › Konferenssiartikkeli › Tieteellinen › vertaisarvioitu
Open accessTiedosto -
On Practical Realisation of Autosegmental Representations in Lexical Transducers of Tonal Bantu Languages
Yli-Jyrä, A., 2020, Proceedings of the Language Technologies for All (LT4All). Adda, G., Choukri, K., Kasinskaite-Buddeberg, I., Mariani, J., Mazo, H. & Sakriani, S. (toim.). Paris: European Language Resources Association (ELRA), s. 346-349 4 SivumääräTutkimustuotos: Artikkeli kirjassa/raportissa/konferenssijulkaisussa › Konferenssiartikkeli › Tieteellinen › vertaisarvioitu
Open accessTiedosto
-
Multilingual Assets and Resources for Mo
Tiedemann, J. (Projektinjohtaja), Attieh, J. (osallistuja), Wang, C. (osallistuja) & Yli-Jyrä, A. (osallistuja)
European Commision Joint Research Centre
01/06/2025 → 30/11/2026
Projekti: The European Research Council: Proof of Consept (ERC-POC)
-
HFST - Helsinki Finite-State Technology
Linden, K. (Principal Investigator), Koskenniemi, K. (Osallistuja), Yli-Jyrä, A. (Osallistuja), Hulden, M. (Osallistuja), Silfverberg, M. (Osallistuja), Pirinen, T. (Osallistuja), Axelson, E. (Osallistuja), Hardwick, S. (Osallistuja), Niemi, J. (Muu) & Hurskainen, A. (Osallistuja)
01/01/2005 → …
Projekti: Tutkimusprojekti
-
GreenNLP: GreenNLP - Att kontrollera koldioxidavtrycket inom hållbar språkteknologi
Tiedemann, J. (Projektinjohtaja), Attieh, J. (osallistuja), Mickus, T. (osallistuja), Nieminen, T. J. (osallistuja), Virpioja, S. P. (osallistuja), Wang, C. (osallistuja), Yli-Jyrä, A. (osallistuja) & Štefánik, M. (osallistuja)
Suomen Akatemia Projektilaskutus
01/01/2023 → 31/12/2025
Projekti: Suomen Akatemia: : Suunnattu akatemiahanke
-
FoTran: Found in Translation - Natural Language Understanding with Cross-Lingual Grounding
Tiedemann, J. (Projektinjohtaja), Attieh, J. (osallistuja), Aulamo, M. (osallistuja), Celikkanat, H. (osallistuja), De Gibert Bonet, O. (osallistuja), Grönroos, S.-A. (osallistuja), Mickus, T. (osallistuja), Scherrer, Y. (osallistuja), Silfverberg, M. (osallistuja), Sjöblom, E. I. (osallistuja), Talman, A. (osallistuja), Vazquez , R. (osallistuja), Virpioja, S. P. (osallistuja), Yli-Jyrä, A. (osallistuja), Celikkanat, H. (Osallistuja), Raganato, A. (Osallistuja), Silfverberg, M. (Osallistuja), Sulubacak, U. (Osallistuja) & Vazquez , R. (Osallistuja)
01/09/2018 → 31/03/2024
Projekti: The European Research Council: Consolidator Grant (H2020-ERC-COG)
-
ADEQSYNTAX: A Usable Finite-State Model for Adequate Syntactic Complexity
Yli-Jyrä, A. (Projektinjohtaja)
01/09/2013 → 30/04/2019
Projekti: Tutkimusprojekti
Tietoaineistot
-
HELFI::Greek1904 -- The Greek New Testament with Lemma and Morphology Data
Yli-Jyrä, A. (Toimittaja), Sandborg-Petersen, U. (Toimittaja), Robinson, M. A. (Toimittaja), dos Santos, D. R. (Tietojen kerääjä) & Nestle, E. (Luoja), Helsingin yliopisto, 2020
https://github.com/amikael/HELFI/tree/master/Greek1904
Tietoaineisto
-
HELFI::Hebrew1008 -- The Hebrew Bible with Lemma and Morphology Data
Yli-Jyrä, A. (Toimittaja), Github, 2020
https://github.com/amikael/HELFI/tree/master/Hebrew1008
Tietoaineisto
-
HELFI::Finnish1938 - The Finnish 1933/1938 Bible Translation with lemmas, morphology and cross-lingual morpheme alignment
Yli-Jyrä, A. (Luoja), Raamatun Tietokirja (RV / Aika / Aikamedia), toukok. 2020
Tietoaineisto
-
HELFI -- a Hebrew-Greek-Finnish Parallel Bible Corpus with Cross-Lingual Morpheme Alignment
Yli-Jyrä, A. (Luoja) & Purhonen, J. (Toimittaja), Helsingin yliopisto, toukok. 2020
https://github.com/amikael/HELFI ja vielä yksi linkki, http://www.islrn.org/resources/840-665-876-625-0/ (näytä vähemmän)
Tietoaineisto
Aktiviteetit
-
Professuurin virantäyttö: opetuksen arviointi (Tapahtuma)
Yli-Jyrä, A. (Jäsen)
21 tammik. 2020Aktiviteetti: Jäsenyystyypit › Jäsenyys tai muu rooli arviointiryhmässä
-
AI Day 2020
Yli-Jyrä, A. (Osallistuja)
26 marrask. 2020Aktiviteetti: Tapahtumaan osallistumisen ja tapahtuman järjestämisen tyypit › Konferensseihin, kursseille ja seminaareihin osallistuminen ja näiden järjestäminen
-
The Rachel and Selim Benin School of Engineering and Computer Science, The Hebrew University of Jerusalem, Israel
Yli-Jyrä, A. (Vieraileva tutkija), Ronning, M. (Muu rooli), Ronning, H. (Muu rooli) & Abend, O. (Muu rooli)
1 tammik. 2020 → 17 tammik. 2020Aktiviteetti: Ulkoisessa instituutiossa vierailun tyypit › Akateeminen vierailu toiseen organisaatioon
-
AI Day 2020 (Tapahtuma)
Yli-Jyrä, A. (Arvioitsija (reviewer))
26 marrask. 2020Aktiviteetti: Julkaisun vertaisarvioinnin ja toimituksellisen työn tyypit › Käsikirjoitusten vertaisarviointi
-
Second International Workshop on Designing Meaning Representations (Tapahtuma)
Yli-Jyrä, A. (Arvioitsija (reviewer))
24 elok. 2020 → 7 lokak. 2020Aktiviteetti: Julkaisun vertaisarvioinnin ja toimituksellisen työn tyypit › Käsikirjoitusten vertaisarviointi
Laitteet
-
nVidia GTX Titan X GPU Workstation in the Department of Digital Humanities at Metsätalo
Yli-Jyrä, A. (Johtaja)
KieliteknologiaLaitteistot/tilat: Laitteet
-
nVidia RTX 2080Ti GPU for a Workstation
Yli-Jyrä, A. (Johtaja)
KieliteknologiaLaitteistot/tilat: Laitteet