Wyniki wyszukiwania - BazTech

1

Learning reduplication with a neural network that lacks explicit variables

Prickett Brandon, Traylor Aaron, Pater Joe

Journal of Language Modelling

|

2022

|

Vol. 10, No.1

1--38

EN

Reduplicative linguistic patterns have been used as evidence for explicit algebraic variables in models of cognition.1 Here, we show that a variable-free neural network can model these patterns in a way that predicts observed human behavior. Specifically, we successfully simulate the three experiments presented by Marcus et al. (1999), as well as Endress et al.’s (2007) partial replication of one of those experiments. We then explore the model’s ability to generalize reduplicative mappings to different kinds of novel inputs. Using Berent’s (2013) scopes of generalization as a metric, we claim that the model matches the scope of generalization that has been observed in humans. We argue that these results challenge past claims about the necessity of symbolic variables in models of cognition.

2

Typology emerges from simplicity in representations and learning

Lambert Dakotah, Rawski Jonathan, Heinz Jeffrey

Journal of Language Modelling

|

2021

|

Vol. 9, No. 1

151--194

EN

We derive well-understood and well-studied subregular classes of formal languages purely from the computational perspective of algorithmic learning problems. We parameterise the learning problem along dimensions of representation and inference strategy. Of special interest are those classes of languages whose learning algorithms are necessarily not prohibitively expensive in space and time, since learners are often exposed to adverse conditions and sparse data. Learned natural language patterns are expected to be most like the patterns in these classes, an expectation supported by previous typological and linguistic research in phonology. A second result is that the learning algorithms presented here are completely agnostic to choice of linguistic representation. In the case of the subregular classes, the results fall out from traditional model-theoretic treatments of words and strings. The same learning algorithms, however, can be applied to model-theoretic treatments of other linguistic representations such as syntactic trees or autosegmental graphs, which opens a useful direction for future research.

3

Modelling a subregular bias in phonological learning with Recurrent Neural Networks

Prickett Brandon

Journal of Language Modelling

|

2021

|

Vol. 9, No. 1

67--96

EN

A number of experiments have demonstrated what seems to be a bias in human phonological learning for patterns that are simpler according to Formal Language Theory (Finley and Badecker 2008; Lai 2015; Avcu 2018). This paper demonstrates that a sequence-to-sequence neural network (Sutskever et al. 2014), which has no such restriction explicitly built into its architecture, can successfully capture this bias. These results suggest that a bias for patterns that are simpler according to Formal Language Theory may not need to be explicitly incorporated into models of phonological learning.

4

Approaching explanatory adequacy in phonology using Minimum Description Length

Rasin Exer, Berger Iddo, Lan Nur, Shefi Itamar, Katzir Roni

Journal of Language Modelling

|

2021

|

Vol. 9, No. 1

17--66

EN

A linguistic theory reaches explanatory adequacy if it arrives at a linguistically-appropriate grammar based on the kind of input available to children. In phonology, we assume that children can succeed even when the input consists of surface evidence alone, with no corrections or explicit paradigmatic information – that is, in learning from distributional evidence. We take the grammar to include both a lexicon of underlying representations and a mapping from the lexicon to surface forms. Moreover, this mapping should be able to express optionality and opacity, among other textbook patterns. This learning challenge has not yet been addressed in the literature. We argue that the principle of Minimum Description Length (MDL) offers the right kind of guidance to the learner – favoring generalizations that are neither overly general nor overly specific – and can help the learner overcome the learning challenge. We illustrate with an implemented MDL learner that succeeds in learning various linguistically-relevant patterns from small corpora.

5

Finite-state Optimality Theory : non-rationality of Harmonic Serialism

Hao Yiding

Journal of Language Modelling

|

2019

|

Vol. 7, No. 2

49--99

EN

This paper analyzes the language-theoretic complexity of Harmonic Serialism (HS), a derivational variant of Optimality Theory. I show that HS can generate non-rational relations using strictly local markedness constraints, proving the “result” of Hao (2017), that HS is rational under those assumptions, to be incorrect. This is possible because deletions performed in a particular order have the ability to enforce nesting dependencies over long distances. I argue that coordinated deletions form a canonical characterization of non-rational relations definable in HS.

6

Rewrite rule gram mars with multitape automata

Hulden M.

Journal of Language Modelling

|

2017

|

Vol. 5, No. 1

107--130

EN

The majority of computational implementations of phonological and morphophonological alternations rely on composing together individual finite state transducers that represent sound changes. Standard composition algorithms do not maintain the intermediate representations between the ultimate input and output forms. These intermedia te strings, however, can be very helpful for various tasks: enriching information (indispensable for models of historical linguistics), providing new avenues to debugging complex grammars, and offering explicit alignment information between morphemes, sound segments, and tags. This paper describes a multitape automaton approach to creating full models of sequences of sound alternation that implement phonological and morphological grammars. A model and a practical implementation of multitape automata is provided together with a multitape composition algorithm tailored to the representation used In this paper. Practical use cases of the approach are illustrated through two common examples: a phonological example of a complex rewrite rule grammar where multiple rules interact and a diachronic ex ample of modeling sound change over time.