TY - GEN
T1 - Quantifying Synthesis and Fusion and their Impact on Machine Translation
AU - Oncevay, Arturo
AU - Ataman, Duygu
AU - van Berkel, Niels
AU - Haddow, Barry
AU - Birch-Mayne, Alexandra
AU - Bjerva, Johannes
N1 - Funding Information:
This work was supported by funding from the European Union's Horizon 2020 research and innovation programme under grant agreements No 825299 (GoURMET) and the EPSRC fellowship grant EP/S001271/1 (MTStretch). Also, we acknowledge the support from eBay. Besides, the study was performed using resources provided by the Cambridge Service for Data Driven Discovery (CSD3) operated by the University of Cambridge Research Computing Service (http://www.csd3.cam.ac.uk/), provided by Dell EMC and Intel using Tier-2 funding from the Engineering and Physical Sciences Research Council (capital grant EP/P020259/1), and DiRAC funding from the Science and Technology Facilities Council (www.dirac.ac.uk). We express our thanks to Kenneth Heafield and Rico Sennrich, who provided us with access to the computing resources. Moreover, the first author was granted financial support from the European Association for Machine Translation (EAMT), under its programme “2020 Sponsorship of Activities”, and from the European Cooperation in Science and Technology (COST) under the programme CA18231 - Multi3Generation: Multi-task, Multilingual, Multimodal Language Generation.
Funding Information:
Moreover, the first author was granted financial support from the European Association for Machine Translation (EAMT), under its programme “2020 Sponsorship of Activities”, and from the European Cooperation in Science and Technology (COST) under the programme CA18231 - Multi3Generation: Multi-task, Multilingual, Multimodal Language Generation.
Funding Information:
This work was supported by funding from the European Union’s Horizon 2020 re search and innovation programme under grant agreements No 825299 (GoURMET) and the EP-SRC fellowship grant EP/S001271/1 (MTStretch). Also, we acknowledge the support from eBay. Besides, the study was performed using resources provided by the Cambridge Service for Data Driven Discovery (CSD3) operated by the University of Cambridge Research Computing Service (http: //www.csd3.cam.ac.uk/), provided by Dell EMC and Intel using Tier-2 funding from the Engineering and Physical Sciences Research Council (capital grant EP/P020259/1), and DiRAC funding from the Science and Technology Facilities Council (www.dirac.ac.uk). We express our thanks to Kenneth Heafield and Rico Sennrich, who provided us with access to the computing resources.
Publisher Copyright:
© 2022 Association for Computational Linguistics.
PY - 2022/7/1
Y1 - 2022/7/1
N2 - Theoretical work in morphological typology offers the possibility of measuring morphological diversity on a continuous scale. However, literature in Natural Language Processing (NLP) typically labels a whole language with a strict type of morphology, e.g. fusional or agglutinative. In this work, we propose to reduce the rigidity of such claims, by quantifying morphological typology at the word and segment level. We consider Payne (2017)’s approach to classify morphology using two indices: synthesis (e.g. analytic to polysynthetic) and fusion (agglutinative to fusional). For computing synthesis, we test unsupervised and supervised morphological segmentation methods for English, German and Turkish, whereas for fusion, we propose a semi-automatic method using Spanish as a case study. Then, we analyse the relationship between machine translation quality and the degree of synthesis and fusion at word (nouns and verbs for English-Turkish, and verbs in English-Spanish) and segment level (previous language pairs plus English-German in both directions). We complement the word-level analysis with human evaluation, and overall, we observe a consistent impact of both indexes on machine translation quality.
AB - Theoretical work in morphological typology offers the possibility of measuring morphological diversity on a continuous scale. However, literature in Natural Language Processing (NLP) typically labels a whole language with a strict type of morphology, e.g. fusional or agglutinative. In this work, we propose to reduce the rigidity of such claims, by quantifying morphological typology at the word and segment level. We consider Payne (2017)’s approach to classify morphology using two indices: synthesis (e.g. analytic to polysynthetic) and fusion (agglutinative to fusional). For computing synthesis, we test unsupervised and supervised morphological segmentation methods for English, German and Turkish, whereas for fusion, we propose a semi-automatic method using Spanish as a case study. Then, we analyse the relationship between machine translation quality and the degree of synthesis and fusion at word (nouns and verbs for English-Turkish, and verbs in English-Spanish) and segment level (previous language pairs plus English-German in both directions). We complement the word-level analysis with human evaluation, and overall, we observe a consistent impact of both indexes on machine translation quality.
M3 - Conference contribution
SP - 1308
EP - 1321
BT - Proceedings of The 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
A2 - Carpuat, Marine
A2 - de Marneffe, Marie-Catherine
A2 - Meza Ruiz, Ivan Vladimir
PB - Association for Computational Linguistics (ACL)
CY - Stroudsburg, PA, USA
T2 - 2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics<br/>
Y2 - 10 July 2022 through 15 July 2022
ER -