Sharon n kirby s
2019Īre we there yet? Encoder-decoder neural networks as cognitive models of English past tense inflection We conclude that modern neural models may still struggle with minority-class generalization. Encoder-decoder models do generalize the most frequently produced plural class, but do not show human-like variability or ‘regular’ extension of these other plural markers. The speaker data show high variability, and two suffixes evince ‘regular’ behavior, appearing more often with phonologically atypical inputs. To investigate this question, we first collect a new dataset from German speakers (production and ratings of plural forms for novel nouns) that is designed to avoid sources of information unavailable to the ED model. (1995): that neural models may learn to extend not the regular, but the most frequent class - and thus fail on tasks like German number inflection, where infrequent suffixes like /-s/ can still be productively generalized. However, their work does not address the criticism raised by Marcus et al. Proceedings of the 58th Annual Meeting of the Association for Computational LinguisticsĬan artificial neural networks learn to represent inflectional morphology and generalize to new words as human speakers do? Kirov and Cotterell (2018) argue that the answer is yes: modern Encoder-Decoder (ED) architectures learn human-like behavior when inflecting English verbs, such as extending the regular past tense form /-(e)d/ to novel words. Inflecting When There’s No Majority: Limitations of Encoder-Decoder Neural Networks as Cognitive Models for German Plurals Finally, we conduct ablation tests that show pitch is the most important acoustic feature for this task and this corpus. We also find that a simple baseline that just predicts a pitch accent on every content word yields 82.2% accuracy, and we suggest that this is the appropriate baseline for this task. We find that these innovations lead to an improvement from 87.5% to 88.7% accuracy on pitch accent detection on American English speech in the Boston University Radio News Corpus, a state-of-the-art result.
#Sharon n kirby s full
Our model makes greater use of context by using full utterances as input and adding an LSTM layer. (2018), who presented a CNN-based model for this task. We propose a new model for pitch accent detection, inspired by the work of Stehwien et al. In order to make this information available to downstream tasks, we need a way to detect prosodic events in speech.
Prosody is a rich information source in natural language, serving as a marker for phenomena such as contrast. Proceedings of the 18th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology We run an additional analysis of the model’s lexical representation space, showing that the two training languages are not fully separated in that space, similarly to the languages of a bilingual human speaker.Īdaptor Grammars for Unsupervised Paradigm Clustering We then test the model on a spoken word processing task, showing that phonology may not be necessary to explain some of the word processing effects observed in non-native speakers. We first show that the model exhibits predictable behaviors on phone-level and word-level discrimination tasks. We train a computational model of phonetic learning, which has no access to phonology, on either one or two languages.
We test an alternative hypothesis: that some of these difficulties can arise from the non-native speakers’ phonetic perception.
Many studies attribute these difficulties to imprecise phonological encoding of words in the lexical memory. Non-native speakers show difficulties with spoken word processing.