Constraint-based Learning of Phonological Processes

Barke, Shraddha; Kunkel, Rose; Polikarpova, Nadia; Meinhardt, Eric; Baković, Eric; Bergen, Leon

doi:10.18653/v1/d19-1639

Cited by 5 publications

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Through his discussion of the distinguishing feature of disjunctive, Baković demonstrated that OT, as a phonological paradigm, is more sophisticated than SPE in many areas [8]. OT has been employed to solve problems in programming language because of its flexibility in taking into account the context dependent changes of sounds [9].…”

Section: Ot As a Framework Of Analysismentioning

confidence: 99%

Conflicts of Vowel Governed Constraints in Arabic Derivation

Al-Hindawi¹,

Al-Jashamy²

2021

ALLC

View full text Add to dashboard Cite

The paradigm of constraints that is proposed by optimality theory as a substitute to the rules paradigm has influenced all the fields of linguistics. Different phonological phenomena in different many languages have been investigated in terms of optimality theory. The phonological structures of Arabic suffer from some changes like deletion, substitution and other processes that underlie the systematic derivation (Al-ishtiqaaq) of vowels. In terms of Optimality Theory, this paper investigates two issues: First, the conflicted faithfulness and markedness constraints that govern vowels through derivation, and second, how these constraints are ranked. Finding out such constraints can provide the storage of the universal constraints by new ones and discovering how Arabic ranks these universal constraints. The current study adopted the mechanism that is proposed by the optimality theory. At the same time, the paper suggested some constraints that has been tested and formulated according to the theory in question. The ranking of these constraints also have been investigated. The study led to demonstrating the existence of the suggested constraints that work during derivation. It also represented how these constraints are ranked. Some of the discovered constraints are already found in the universal storage of constraints and others are peculiar to Arabic. It is found that the SAK constraint (the absence of the Arabic short vowels) plays a fundamental role in vowels derivation.

show abstract

Section: Ot As a Framework Of Analysismentioning

confidence: 99%

Conflicts of Vowel Governed Constraints in Arabic Derivation

Al-Hindawi¹,

Al-Jashamy²

2021

ALLC

View full text Add to dashboard Cite

show abstract

“…We pursue a similar goal, but in a few-shot setting. Barke et al (2019) and Ellis et al (2015) study program synthesis applied to linguistic rule learning. They make much stronger assumptions about the data (the existence of an underlying form, and the availability of additional information like IPA features).…”

Section: Global Constraintsmentioning

confidence: 99%

Sample-efficient Linguistic Generalizations through Program Synthesis: Experiments with Phonology Problems

Saujas¹,

Sathe²,

Choudhury³

et al. 2021

Preprint

View full text Add to dashboard Cite

Neural models excel at extracting statistical patterns from large amounts of data, but struggle to learn patterns or reason about language from only a few examples. In this paper, we ask: Can we learn explicit rules that generalize well from only a few examples? We explore this question using program synthesis. We develop a synthesis model to learn phonology rules as programs in a domain-specific language. We test the ability of our models to generalize from few training examples using our new dataset of problems from the Linguistics Olympiad, a challenging set of tasks that require strong linguistic reasoning ability. In addition to being highly sample-efficient, our approach generates human-readable programs, and allows control over the generalizability of the learnt programs.

show abstract

Synthesizing theories of human language with Bayesian program induction

et al. 2022

View full text Add to dashboard Cite

Automated, data-driven construction and evaluation of scientific models and theories is a long-standing challenge in artificial intelligence. We present a framework for algorithmically synthesizing models of a basic part of human language: morpho-phonology, the system that builds word forms from sounds. We integrate Bayesian inference with program synthesis and representations inspired by linguistic theory and cognitive models of learning and discovery. Across 70 datasets from 58 diverse languages, our system synthesizes human-interpretable models for core aspects of each language’s morpho-phonology, sometimes approaching models posited by human linguists. Joint inference across all 70 data sets automatically synthesizes a meta-model encoding interpretable cross-language typological tendencies. Finally, the same algorithm captures few-shot learning dynamics, acquiring new morphophonological rules from just one or a few examples. These results suggest routes to more powerful machine-enabled discovery of interpretable models in linguistics and other scientific domains.

show abstract

Constraint-based Learning of Phonological Processes

Cited by 5 publications

References 21 publications

Conflicts of Vowel Governed Constraints in Arabic Derivation

Conflicts of Vowel Governed Constraints in Arabic Derivation

Sample-efficient Linguistic Generalizations through Program Synthesis: Experiments with Phonology Problems

Synthesizing theories of human language with Bayesian program induction

Contact Info

Product

Resources

About