Weak semantic context helps phonetic learning in a model of infant language acquisition
Weak semantic context helps phonetic learning in a model of infant language acquisition
复制标题
DOI：
10.3115/v1/p14-1101
复制
发表时间：
2014-06
期刊：
影响因子：
--
通讯作者：
Stella Frank;Naomi H Feldman;S. Goldwater
中科院分区：
文献类型：
--
作者：
Stella Frank;Naomi H Feldman;S. Goldwater
语音范畴的学习是语言学习的第一步，但仅仅利用语音的分布信息是很难做到的。语义学可能是有用的，因为具有不同含义的单词有不同的语音，但目前还不清楚有多少单词的含义是已知的婴儿学习语音类别。我们表明，参加一个较弱的语义源，在当前的背景下，在主题的分布形式，可以导致语音类别学习的改善。在我们的模型中，联合词的形式和语音类别推理的先前模型的扩展，词的形式的概率是主题相关的，使该模型能够找到更好的语音元音类别和词的形式比没有语义知识的模型。
Learning phonetic categories is one of the first steps to learning a language, yet is hard to do using only distributional phonetic information. Semantics could potentially be useful, since words with different meanings have distinct phonetics, but it is unclear how many word meanings are known to infants learning phonetic categories. We show that attending to a weaker source of semantics, in the form of a distribution over topics in the current context, can lead to improvements in phonetic category learning. In our model, an extension of a previous model of joint word-form and phonetic category inference, the probability of word-forms is topic-dependent, enabling the model to find significantly better phonetic vowel categories and word-forms than a model with no semantic knowledge.