Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP

Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP Lisa Beinborn editor Koustava Goswami editor Saliha Muradoğlu editor Alexey Sorokin editor Ritesh Kumar editor Andreas Shcherbakov editor Edoardo M Ponti editor Ryan Cotterell editor Ekaterina Vylomova editor 2023-05 Association for Computational Linguistics Dubrovnik, Croatia text conference publication sigtyp-2023-research https://aclanthology.org/2023.sigtyp-1.0/ You Can Have Your Data and Balance It Too: Towards Balanced and Efficient Multilingual Models Tomasz Limisiewicz author Dan Malkin author Gabriel Stanovsky author 2023-05 text Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP Lisa Beinborn editor Koustava Goswami editor Saliha Muradoğlu editor Alexey Sorokin editor Ritesh Kumar editor Andreas Shcherbakov editor Edoardo M Ponti editor Ryan Cotterell editor Ekaterina Vylomova editor Association for Computational Linguistics Dubrovnik, Croatia conference publication limisiewicz-etal-2023-data 10.18653/v1/2023.sigtyp-1.1 https://aclanthology.org/2023.sigtyp-1.1/ 2023-05 1 11 Multilingual End-to-end Dependency Parsing with Linguistic Typology knowledge Chinmay Choudhary author Colm O’riordan author 2023-05 text Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP Lisa Beinborn editor Koustava Goswami editor Saliha Muradoğlu editor Alexey Sorokin editor Ritesh Kumar editor Andreas Shcherbakov editor Edoardo M Ponti editor Ryan Cotterell editor Ekaterina Vylomova editor Association for Computational Linguistics Dubrovnik, Croatia conference publication choudhary-oriordan-2023-multilingual 10.18653/v1/2023.sigtyp-1.2 https://aclanthology.org/2023.sigtyp-1.2/ 2023-05 12 21 Identifying the Correlation Between Language Distance and Cross-Lingual Transfer in a Multilingual Representation Space Fred Philippy author Siwen Guo author Shohreh Haddadan author 2023-05 text Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP Lisa Beinborn editor Koustava Goswami editor Saliha Muradoğlu editor Alexey Sorokin editor Ritesh Kumar editor Andreas Shcherbakov editor Edoardo M Ponti editor Ryan Cotterell editor Ekaterina Vylomova editor Association for Computational Linguistics Dubrovnik, Croatia conference publication philippy-etal-2023-identifying 10.18653/v1/2023.sigtyp-1.3 https://aclanthology.org/2023.sigtyp-1.3/ 2023-05 22 29 Using Modern Languages to Parse Ancient Ones: a Test on Old English Luca Brigada Villa author Martina Giarda author 2023-05 text Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP Lisa Beinborn editor Koustava Goswami editor Saliha Muradoğlu editor Alexey Sorokin editor Ritesh Kumar editor Andreas Shcherbakov editor Edoardo M Ponti editor Ryan Cotterell editor Ekaterina Vylomova editor Association for Computational Linguistics Dubrovnik, Croatia conference publication brigada-villa-giarda-2023-using 10.18653/v1/2023.sigtyp-1.4 https://aclanthology.org/2023.sigtyp-1.4/ 2023-05 30 41 The Denglisch Corpus of German-English Code-Switching Doreen Osmelak author Shuly Wintner author 2023-05 text Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP Lisa Beinborn editor Koustava Goswami editor Saliha Muradoğlu editor Alexey Sorokin editor Ritesh Kumar editor Andreas Shcherbakov editor Edoardo M Ponti editor Ryan Cotterell editor Ekaterina Vylomova editor Association for Computational Linguistics Dubrovnik, Croatia conference publication osmelak-wintner-2023-denglisch 10.18653/v1/2023.sigtyp-1.5 https://aclanthology.org/2023.sigtyp-1.5/ 2023-05 42 51 Trimming Phonetic Alignments Improves the Inference of Sound Correspondence Patterns from Multilingual Wordlists Frederic Blum author Johann-Mattis List author 2023-05 text Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP Lisa Beinborn editor Koustava Goswami editor Saliha Muradoğlu editor Alexey Sorokin editor Ritesh Kumar editor Andreas Shcherbakov editor Edoardo M Ponti editor Ryan Cotterell editor Ekaterina Vylomova editor Association for Computational Linguistics Dubrovnik, Croatia conference publication blum-list-2023-trimming 10.18653/v1/2023.sigtyp-1.6 https://aclanthology.org/2023.sigtyp-1.6/ 2023-05 52 64 A Crosslinguistic Database for Combinatorial and Semantic Properties of Attitude Predicates Deniz Özyıldız author Ciyang Qing author Floris Roelofsen author Maribel Romero author Wataru Uegaki author 2023-05 text Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP Lisa Beinborn editor Koustava Goswami editor Saliha Muradoğlu editor Alexey Sorokin editor Ritesh Kumar editor Andreas Shcherbakov editor Edoardo M Ponti editor Ryan Cotterell editor Ekaterina Vylomova editor Association for Computational Linguistics Dubrovnik, Croatia conference publication ozyildiz-etal-2023-crosslinguistic 10.18653/v1/2023.sigtyp-1.7 https://aclanthology.org/2023.sigtyp-1.7/ 2023-05 65 75 Corpus-based Syntactic Typological Methods for Dependency Parsing Improvement Diego Alves author Božo Bekavac author Daniel Zeman author Marko Tadić author 2023-05 text Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP Lisa Beinborn editor Koustava Goswami editor Saliha Muradoğlu editor Alexey Sorokin editor Ritesh Kumar editor Andreas Shcherbakov editor Edoardo M Ponti editor Ryan Cotterell editor Ekaterina Vylomova editor Association for Computational Linguistics Dubrovnik, Croatia conference publication alves-etal-2023-corpus 10.18653/v1/2023.sigtyp-1.8 https://aclanthology.org/2023.sigtyp-1.8/ 2023-05 76 88 Cross-lingual Transfer Learning with Persian Sepideh Mollanorozy author Marc Tanti author Malvina Nissim author 2023-05 text Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP Lisa Beinborn editor Koustava Goswami editor Saliha Muradoğlu editor Alexey Sorokin editor Ritesh Kumar editor Andreas Shcherbakov editor Edoardo M Ponti editor Ryan Cotterell editor Ekaterina Vylomova editor Association for Computational Linguistics Dubrovnik, Croatia conference publication mollanorozy-etal-2023-cross 10.18653/v1/2023.sigtyp-1.9 https://aclanthology.org/2023.sigtyp-1.9/ 2023-05 89 95 Information-Theoretic Characterization of Vowel Harmony: A Cross-Linguistic Study on Word Lists Julius Steuer author Johann-Mattis List author Badr M Abdullah author Dietrich Klakow author 2023-05 text Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP Lisa Beinborn editor Koustava Goswami editor Saliha Muradoğlu editor Alexey Sorokin editor Ritesh Kumar editor Andreas Shcherbakov editor Edoardo M Ponti editor Ryan Cotterell editor Ekaterina Vylomova editor Association for Computational Linguistics Dubrovnik, Croatia conference publication steuer-etal-2023-information 10.18653/v1/2023.sigtyp-1.10 https://aclanthology.org/2023.sigtyp-1.10/ 2023-05 96 109 Revisiting Dependency Length and Intervener Complexity Minimisation on a Parallel Corpus in 35 Languages Andrew Thomas Dyer author 2023-05 text Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP Lisa Beinborn editor Koustava Goswami editor Saliha Muradoğlu editor Alexey Sorokin editor Ritesh Kumar editor Andreas Shcherbakov editor Edoardo M Ponti editor Ryan Cotterell editor Ekaterina Vylomova editor Association for Computational Linguistics Dubrovnik, Croatia conference publication dyer-2023-revisiting 10.18653/v1/2023.sigtyp-1.11 https://aclanthology.org/2023.sigtyp-1.11/ 2023-05 110 119 Does Topological Ordering of Morphological Segments Reduce Morphological Modeling Complexity? A Preliminary Study on 13 Languages Andreas Shcherbakov author Ekaterina Vylomova author 2023-05 text Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP Lisa Beinborn editor Koustava Goswami editor Saliha Muradoğlu editor Alexey Sorokin editor Ritesh Kumar editor Andreas Shcherbakov editor Edoardo M Ponti editor Ryan Cotterell editor Ekaterina Vylomova editor Association for Computational Linguistics Dubrovnik, Croatia conference publication shcherbakov-vylomova-2023-topological 10.18653/v1/2023.sigtyp-1.12 https://aclanthology.org/2023.sigtyp-1.12/ 2023-05 120 125 Findings of the SIGTYP 2023 Shared task on Cognate and Derivative Detection For Low-Resourced Languages Priya Rani author Koustava Goswami author Adrian Doyle author Theodorus Fransen author Bernardo Stearns author John P McCrae author 2023-05 text Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP Lisa Beinborn editor Koustava Goswami editor Saliha Muradoğlu editor Alexey Sorokin editor Ritesh Kumar editor Andreas Shcherbakov editor Edoardo M Ponti editor Ryan Cotterell editor Ekaterina Vylomova editor Association for Computational Linguistics Dubrovnik, Croatia conference publication rani-etal-2023-findings 10.18653/v1/2023.sigtyp-1.13 https://aclanthology.org/2023.sigtyp-1.13/ 2023-05 126 131 ÚFAL Submission for SIGTYP Supervised Cognate Detection Task Tomasz Limisiewicz author 2023-05 text Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP Lisa Beinborn editor Koustava Goswami editor Saliha Muradoğlu editor Alexey Sorokin editor Ritesh Kumar editor Andreas Shcherbakov editor Edoardo M Ponti editor Ryan Cotterell editor Ekaterina Vylomova editor Association for Computational Linguistics Dubrovnik, Croatia conference publication limisiewicz-2023-ufal 10.18653/v1/2023.sigtyp-1.14 https://aclanthology.org/2023.sigtyp-1.14/ 2023-05 132 136 CoToHiLi at SIGTYP 2023: Ensemble Models for Cognate and Derivative Words Detection Liviu P Dinu author Ioan-Bogdan Iordache author Ana Sabina Uban author 2023-05 text Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP Lisa Beinborn editor Koustava Goswami editor Saliha Muradoğlu editor Alexey Sorokin editor Ritesh Kumar editor Andreas Shcherbakov editor Edoardo M Ponti editor Ryan Cotterell editor Ekaterina Vylomova editor Association for Computational Linguistics Dubrovnik, Croatia conference publication dinu-etal-2023-cotohili 10.18653/v1/2023.sigtyp-1.15 https://aclanthology.org/2023.sigtyp-1.15/ 2023-05 137 142 Multilingual BERT has an Accent: Evaluating English Influences on Fluency in Multilingual Models Isabel Papadimitriou author Kezia Lopez author Dan Jurafsky author 2023-05 text Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP Lisa Beinborn editor Koustava Goswami editor Saliha Muradoğlu editor Alexey Sorokin editor Ritesh Kumar editor Andreas Shcherbakov editor Edoardo M Ponti editor Ryan Cotterell editor Ekaterina Vylomova editor Association for Computational Linguistics Dubrovnik, Croatia conference publication papadimitriou-etal-2023-multilingual-bert 10.18653/v1/2023.sigtyp-1.16 https://aclanthology.org/2023.sigtyp-1.16/ 2023-05 143 146 Grambank’s Typological Advances Support Computational Research on Diverse Languages Hannah J Haynie author Damián Blasi author Hedvig Skirgård author Simon J Greenhill author Quentin D Atkinson author Russell D Gray author 2023-05 text Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP Lisa Beinborn editor Koustava Goswami editor Saliha Muradoğlu editor Alexey Sorokin editor Ritesh Kumar editor Andreas Shcherbakov editor Edoardo M Ponti editor Ryan Cotterell editor Ekaterina Vylomova editor Association for Computational Linguistics Dubrovnik, Croatia conference publication haynie-etal-2023-grambanks 10.18653/v1/2023.sigtyp-1.17 https://aclanthology.org/2023.sigtyp-1.17/ 2023-05 147 149 Language-Agnostic Measures Discriminate Inflection and Derivation Coleman Haley author Edoardo M Ponti author Sharon Goldwater author 2023-05 text Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP Lisa Beinborn editor Koustava Goswami editor Saliha Muradoğlu editor Alexey Sorokin editor Ritesh Kumar editor Andreas Shcherbakov editor Edoardo M Ponti editor Ryan Cotterell editor Ekaterina Vylomova editor Association for Computational Linguistics Dubrovnik, Croatia conference publication haley-etal-2023-language 10.18653/v1/2023.sigtyp-1.18 https://aclanthology.org/2023.sigtyp-1.18/ 2023-05 150 152 Gradual Language Model Adaptation Using Fine-Grained Typology Marcell Richard Fekete author Johannes Bjerva author 2023-05 text Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP Lisa Beinborn editor Koustava Goswami editor Saliha Muradoğlu editor Alexey Sorokin editor Ritesh Kumar editor Andreas Shcherbakov editor Edoardo M Ponti editor Ryan Cotterell editor Ekaterina Vylomova editor Association for Computational Linguistics Dubrovnik, Croatia conference publication fekete-bjerva-2023-gradual 10.18653/v1/2023.sigtyp-1.19 https://aclanthology.org/2023.sigtyp-1.19/ 2023-05 153 158 On the Nature of Discrete Speech Representations in Multilingual Self-supervised Models Badr M Abdullah author Mohammed Maqsood Shaik author Dietrich Klakow author 2023-05 text Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP Lisa Beinborn editor Koustava Goswami editor Saliha Muradoğlu editor Alexey Sorokin editor Ritesh Kumar editor Andreas Shcherbakov editor Edoardo M Ponti editor Ryan Cotterell editor Ekaterina Vylomova editor Association for Computational Linguistics Dubrovnik, Croatia conference publication abdullah-etal-2023-nature 10.18653/v1/2023.sigtyp-1.20 https://aclanthology.org/2023.sigtyp-1.20/ 2023-05 159 161