Constraint-based Learning of Phonological Processes

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, pages 6176–6186, Hong Kong, China, November 3–7, 2019. c⃝2019 Association for Computational Linguistics 6176 Constraint-based Learning of Phonological Processes Shraddha Barke, Rose Kunkel, Nadia Polikarpova, Eric Meinhardt, Eric Bakovi´c, and Leon Bergen {sbarke,wkunkel,npolikarpova,emeinhar,ebakovic,lbergen} @ucsd.edu University of California, San Diego Abstract Phonological processes are context-dependent sound changes in natural languages. We present an unsupervised approach to learning human-readable descriptions of phonological processes from collections of related utter- ances. Our approach builds upon a technique from the programming languages community called constraint-based program synthesis. We contribute a novel encoding of the learning problem into Satisfiablity Modulo Theory constraints, which enables both data efficiency and fast inference. We evaluate our system on textbook phonology problems and lexical databases, and show that it achieves high accuracy at speeds two orders of magnitude faster than state-of-the-art approaches. 1 Introduction Phonological processes govern the way speech sounds in natural languages change depending on the context. For example, in English verbs, the past tense suffix /d/ turns into [t] after voiceless consonants (so the word “zipped” is pronounced [zIpt], while “begged” is pronounced [bEgd]). Linguists routinely face the task of inferring phonological processes by observing and contrasting surface forms (pronun- ciations) of morphologically related words. To aid linguists with this task, we consider the problem of learning phonological processes automatically from collections of related surface forms. This problem setting imposes four core require- ments, which guide the design of our approach: 1. Inference results must be fully interpretable: our goal is to explain phonological processes exhibited by the data, not merely predict pro- nunciations of unseen words. Hence, our model takes the form of discrete, conditional rewrite rules from rule-based phonology (Chomsky and Halle, 1968). 2. Inference must be unsupervised: phonological processes are formalized as transformations from (latent) underlying forms to surface forms (rather than between surface forms). 3. Inference must be data-efficient: typically only a handful of data points are available. 4. Inference must be fast: we envision linguists using our system interactively, tweaking the data and being able to see the inferred rules within minutes. Recently program synthesis has emerged as a promising approach to interpretable and data- efficient learning (Ellis et al., 2015; Singh et al., 2017; Verma et al., 2018; Ellis et al., 2018). In program synthesis, models are represented as programs in a domain-specific language (DSL), which allows domain experts to impose a strong prior by designing an appropriate DSL. Program synthesis uses powerful constraint solvers to perform combinatorial optimiza- tion and find the least-cost program in the DSL that fits the data. Program synthesis has been previously used to tackle the problem of phonological rule learning (Ellis et al., 2015), however their work uses global inference which scales poorly and hence does not satisfy requirement 4 (their system takes an hour on average to solve a phonology textbook problem). In this work, we propose a novel inference tech- nique …

Content truncated to 500 words