Ab Antiquo: Neural Proto-language Reconstruction

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4460–4473 June 6–11, 2021. ©2021 Association for Computational Linguistics 4460 Ab Antiquo: Neural Proto-language Reconstruction Carlo Meloni∗1 Shauli Ravfogel∗2,3 Yoav Goldberg2,3 1Department of Comparative Language Science, University of Zurich 2Computer Science Department, Bar Ilan University 3Allen Institute for Artificial Intelligence carlomeloni@mail.tau.ac.il, {shauli.ravfogel, yoav.goldberg}@gmail.com Abstract Historical linguists have identified regularities in the process of historic sound change. The comparative method utilizes those regularities to reconstruct proto-words based on observed forms in daughter languages. Can this pro- cess be efficiently automated? We address the task of proto-word reconstruction, in which the model is exposed to cognates in contempo- rary daughter languages, and has to predict the proto word in the ancestor language. We pro- vide a novel dataset for this task, encompass- ing over 8,000 comparative entries, and show that neural sequence models outperform con- ventional methods applied to this task so far. Error analysis reveals a variability in the abil- ity of neural model to capture different phono- logical changes, correlating with the complex- ity of the changes. Analysis of learned embed- dings reveals the models learn phonologically meaningful generalizations, corresponding to well-attested phonological shifts documented by historical linguistics. 1 Introduction Historical linguists seek to identify and explain the various ways in which languages change through time. Research in historical linguistics has re- vealed that groups of languages (language fami- lies) can often be traced into a common, ancestral language, a “proto-language”. Large-scale lexical comparison of words across different languages enables linguists to identify cognates: words shar- ing a common proto-word. Comparing cognates makes it possible to identify rules of phonetic his- toric change, and by back-tracing those rules one can identify the form of the proto-word, which is often not documented. That methodology is called the comparative method (Anttila, 1989), and is the main tool used to reconstruct the lex- icon and phonology of extinct languages. Infer- ring the form of proto-words from existing cog- ∗Equal contribution nates in daughter languages is possible since his- torical sound changes within a language family are not random. Rather, the phonological change is characterized by regularities that are the result of constraints imposed by the human articulatory and cognitive faculties (Millar, 2013). For exam- ple, we can find such regular change—commonly called “systematic correspondence”—by looking at the evolution of the first phoneme of Latin’s word for “sky”:1 Figure 1: the evolution of Latin word for “sky” is sev- eral Romance languages. The Spanish word’s first sound is [T], while the Italian word begins with [tS], the French word with [s], Romansh with [ts] and Sardinian with [k]. This pattern is systematic, and will be found throughout the languages. Working this way, his- torical linguists reconstruct words in the proto- language from existing cognates in the daughter languages, and determine how words in the proto- language may have sounded. To what extent can a machine-learning model learn to reconstruct proto-words from examples in this …

Content truncated to 500 words