paper-with-me

홈 › Papers

Do RNN States Encode Abstract Phonological Processes?

2021-04-01 · Miikka Silfverberg, Francis Tyers, Garrett Nicolai, Mans Hulden

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 direction of the gradation.

📄 PDF Abstract BibTeX arXiv:2104.00789

Code (0)

등록된 구현이 없습니다.

Tasks

MemorizationMorphological Inflection

Similar Papers 제목 키워드 기반

Do RNN States Encode Abstract Phonological Alternations?

2021-06-01 · NAACL 2021 4 · Miikka Silfverberg, Francis Tyers, Garrett Nicolai, Mans Hulden

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 pe…

MemorizationMorphological Inflection

Markov Abstractions for PAC Reinforcement Learning in Non-Markov Decision Processes

2022-04-29 · Alessandro Ronca, Gabriel Paludo Licks, Giuseppe De Giacomo

Our work aims at developing reinforcement learning algorithms that do not rely on the Markov assumption. We consider the class of Non-Markov Decision Processes where histories can be abstracted into a finite set of state…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Layer-wise Probing of wav2vec 2.0 and Whisper for Consonant Cluster Reduction in African American English

2026-06-22 · Hamid Mojarad, Kevin Tang arxiv

Self-supervised and supervised speech models are increasingly used to investigate which linguistic information their internal representations encode, and at what level of abstraction they encode it. One underexplored phe…

Speech Recognition

Constraint-based Learning of Phonological Processes

2019-11-01 · IJCNLP 2019 11 · Shraddha Barke, Rose Kunkel, Nadia Polikarpova, Eric Meinhardt 외

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 utterance…

Program Synthesis

Encoder-decoder models for latent phonological representations of words

2019-08-01 · WS 2019 8 · Cass Jacobs, ra L., Fred Mailhot

We use sequence-to-sequence networks trained on sequential phonetic encoding tasks to construct compositional phonological representations of words. We show that the output of an encoder network can predict the phonetic …

Decoder