From Segmentation to Analyses: a Probabilistic Model for Unsupervised Morphology Induction

Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 337–346, Valencia, Spain, April 3-7, 2017. c⃝2017 Association for Computational Linguistics From Segmentation to Analyses: A Probabilistic Model for Unsupervised Morphology Induction Toms Bergmanis School of Informatics University of Edinburgh T.Bergmanis@sms.ed.ac.uk Sharon Goldwater School of Informatics University of Edinburgh sgwater@inf.ed.ac.uk Abstract A major motivation for unsupervised mor- phological analysis is to reduce the sparse data problem in under-resourced languages. Most previous work focuses on segmenting surface forms into their constituent morphs (e.g., taking: tak +ing), but surface form segmentation does not solve the sparse data problem as the analyses of take and taking are not connected to each other. We extend the MorphoChains system (Narasimhan et al., 2015) to provide morphological anal- yses that can abstract over spelling dif- ferences in functionally similar morphs. These analyses are not required to use all the orthographic material of a word (stop- ping: stop +ing), nor are they limited to only that material (acidified: acid +ify +ed). On average across six typologically varied languages our system has a similar or better F-score on EMMA (a measure of underlying morpheme accuracy) than three strong baselines; moreover, the total num- ber of distinct morphemes identified by our system is on average 12.8% lower than for Morfessor (Virpioja et al., 2013), a state- of-the-art surface segmentation system. 1 Introduction Most previous work on unsupervised morphologi- cal analysis has focused on the problem of segmen- tation: segmenting surface forms into their con- stituent morphs (Goldsmith, 2001; Creutz and La- gus, 2007; Poon et al., 2009; Lee et al., 2011; Virpi- oja et al., 2013; Sirts and Goldwater, 2013). How- ever, the focus on surface segmentation is largely due to ease of model definition and implementa- tion rather than linguistic correctness. Even in lan- guages with primarily concatenative morphology, spelling (or phonological) changes often occur at morpheme boundaries, so that a single morpheme may have multiple surface forms. For example, the past tense in English may surface as -ed (walked), -d (baked), -ted (emitted), -ped (skipped), etc. A major motivation for unsupervised morpholog- ical analysis is to reduce the sparse data problem in under-resourced languages. While surface segmen- tation can help, the example above illustrates its limitations: for more effective parameter sharing, a system should recognize that -ed, -d, -ted, and -ped share the same linguistic function. The importance of identifying underlying morphemes rather than surface morphs is widely recognized, for example by the MorphoChallenge organizers, who in later years provided datasets and evaluation measures to encourage this deeper level of analysis (Kurimo et al., 2010). Nevertheless, only a few systems have attempted this task (Goldwater and Johnson, 2004; Naradowsky and Goldwater, 2009), and as far as we know, only one, the rule-based MORSEL (Lig- nos et al., 2009; Lignos, 2010), has come close to the level of performance achieved by segmentation systems such as Morfessor (Virpioja et al., 2013). We present a system that adapts the unsupervised …

Content truncated to 500 words