1 |
Do RNN States Encode Abstract Phonological Processes? ...
|
|
|
|
Abstract:
Sequence-to-sequence models have delivered impressive results in word formation tasks such as morphological inflection, often learning to model subtle morphophonological details with limited training data. Despite the performance, the opacity of neural models makes it difficult to determine whether complex generalizations are learned, or whether a kind of separate rote memorization of each morphophonological process takes place. To investigate whether complex alternations are simply memorized or whether there is some level of generalization across related sound changes in a sequence-to-sequence model, we perform several experiments on Finnish consonant gradation -- a complex set of sound changes triggered in some words by certain suffixes. We find that our models often -- though not always -- encode 17 different consonant gradation processes in a handful of dimensions in the RNN. We also show that by scaling the activations in these dimensions we can control whether consonant gradation occurs and the ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.2104.00789 https://arxiv.org/abs/2104.00789
|
|
BASE
|
|
Hide details
|
|
2 |
Can a Transformer Pass the Wug Test? Tuning Copying Bias in Neural Morphological Inflection Models ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
SIGMORPHON 2020 Shared Task 0: Typologically Diverse Morphological Inflection ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
The SIGMORPHON 2019 Shared Task: Morphological Analysis in Context and Cross-Lingual Transfer for Inflection ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Marrying Universal Dependencies and Universal Morphology ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
On the Complexity and Typology of Inflectional Morphological Systems ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
A Comparison of Feature-Based and Neural Scansion of Poetry ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|