Can Neural Adaptation Explain Word Choice?
نویسندگان
چکیده
Speakers refer to objects using terms on various levels of description. Labeling a poodle, they use the subordinate term “poodle” or the basic term “dog”. Our model attributes these effects to visual context, relying on the domain general mechanism of neural adaptation. Two SOMs represent visual and auditory categories. Word learning is modeled via simultaneous presentation of item and word form and the creation of Hebbian synapses. Neural adaptation causes a decrease of activation in repeatedly activated nodes. We predicted that as a result of this, when presented alone or alongside a distractor from another basic category, an item will be referred to by its basic term, while the presence of a distractor from the same basic category will induce a shift to the target’s subordinate label. Three simulations taking into account the relative frequency of an item's basic and subordinate level labels supported this hypothesis.
منابع مشابه
Fast Gated Neural Domain Adaptation: Language Model as a Case Study
Neural network training has been shown to be advantageous in many natural language processing applications, such as language modelling or machine translation. In this paper, we describe in detail a novel domain adaptation mechanism in neural network training. Instead of learning and adapting the neural network on millions of training sentences – which can be very timeconsuming or even infeasibl...
متن کاملConcept Form Adaptation in Human-Computer Dialog
In this work we examine user adaptation to a dialog system’s choice of realization of task-related concepts. We analyze forms of the time concept in the Let’s Go! spoken dialog system. We find that users adapt to the system’s choice of time form. We also find that user adaptation is affected by perceived system adaptation. This means that dialog systems can guide users’ word choice and can adap...
متن کاملUnsupervised adaptation for deep neural network using linear least square method
In this paper, we propose a novel model based adaptation for deep neural networks based on a linear least square method. Our proposed algorithm can perform unsupervised adaptation even if the auto transcripts may have 60-70% of word error rate. We evaluate our algorithm on low resource languages, from the the IARPA BABEL program, such as Assamese, Bengali, Haitian Creole, Lao and Zulu. Our expe...
متن کاملAddressing Domain Adaptation for Chinese Word Segmentation with Global Recurrent Structure
Boundary features are widely used in traditional Chinese Word Segmentation (CWS) methods as they can utilize unlabeled data to help improve the Out-ofVocabulary (OOV) word recognition performance. Although various neural network methods for CWS have achieved performance competitive with state-of-the-art systems, these methods, constrained by the domain and size of the training corpus, do not wo...
متن کاملUnsupervised Domain Adaptation for Word Sense Disambiguation using Stacked Denoising Autoencoder
In this paper, we propose an unsupervised domain adaptation for Word Sense Disambiguation (WSD) using Stacked Denoising Autoencoder (SdA). SdA is an unsupervised learning method of obtaining the abstract feature set of input data using Neural Network. The abstract feature set absorbs the difference of domains, and thus SdA can solve a problem of domain adaptation. However, SdA does not always c...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2011