Comparing Statistical and Neural Models for Learning Sound Correspondences
Cognate prediction and proto-form reconstruction are key tasks in computational historical linguistics that rely on the study of sound change regularity. Solving these tasks appears to be very similar to machine translation, though methods from that field have barely been applied to historical linguistics. Therefore, in this paper, we investigate the learnability of sound correspondences between a proto-language and daughter languages for two machine-translation-inspired models, one statistical, the other neural. We first carry out our experiments on plausible artificial languages, without noise, in order to study the role of each parameter on the algorithms respective performance under almost perfect conditions. We then study real languages, namely Latin, Italian and Spanish, to see if those performances generalise well. We show that both model types manage to learn sound changes despite data scarcity, although the best performing model type depends on several parameters such as the size of the training data, the ambiguity, and the prediction direction.
Code (1)
Tasks
Cognate PredictionMachine TranslationTranslationSimilar Papers 제목 키워드 기반
Are Sounds Sound for Phylogenetic Reconstruction?
In traditional studies on language evolution, scholars often emphasize the importance of sound laws and sound correspondences for phylogenetic inference of language family trees. However, to date, computational approache…
Taste-aware music retrieval from audio embeddings
Crossmodal correspondences between sound and taste are well established in psychology and neuroscience, but largely absent from content-based multimedia retrieval. We formalise taste-from-audio prediction as a content-ba…
Information RetrievalUnsupervised Audio-Caption Aligning Learns Correspondences between Individual Sound Events and Textual Phrases
We investigate unsupervised learning of correspondences between sound events and textual phrases through aligning audio clips with textual captions describing the content of a whole audio clip. We align originally unalig…
Event DetectionRetrievalSound Event DetectionAdaStop: adaptive statistical testing for sound comparisons of Deep RL agents
Recently, the scientific community has questioned the statistical reproducibility of many empirical results, especially in the field of machine learning. To contribute to the resolution of this reproducibility crisis, we…
Deep Reinforcement LearningMuJoCoReinforcement Learning (RL)Sound Localization by Self-Supervised Time Delay Estimation
Sounds reach one microphone in a stereo pair sooner than the other, resulting in an interaural time delay that conveys their directions. Estimating a sound's time delay requires finding correspondences between the signal…
Contrastive LearningVisual Tracking