Tree automata are a fundamental tool in computer science. We report on experiments to integrate tree automata in Coq using shallow and deep reflection techniques. While shallow reflection seems more natural in this context, it turns out to give disappointing results. Deep reflection is more difficult to apply, but is more promising.

When compiling embedded languages it is natural to use an abstract syntax tree to represent programs. This is known as a deep embedding and it is a rather cumbersome technique compared to other forms of embedding, typically leading to more code and being harder to extend. In shallow embeddings, language constructs are mapped directly to their semantics which yields more flexible and succinct im...

This paper presents a strategy for a syntax based ranking of documents specifically orientedto Question Answering (QA). This strategy should limit the number of documents, processed byan answer extraction module of an syntax oriented QA system. Several measures for statisticalscoring of expressions are presented and evaluated on 400 factoid questions from the TREC-12competition....

Dropout has been witnessed with great success in training deep neural networks by independently zeroing out the outputs of neurons at random. It has also received a surge of interest for shallow learning, e.g., logistic regression. However, the independent sampling for dropout could be suboptimal for the sake of convergence. In this paper, we propose to use multinomial sampling for dropout, i.e...

Because the criteria for success differ across various domains of life, no single normative standard will ever work for all types of thinking. One method for dealing with this apparent dilemma is to propose that the mind is made up of a large number of specialized modules. This review describes how this multi-modular framework for the mind overcomes several critical conceptual and theoretical c...

In the presence of rst-class continuations, shallow maintenance of dynamic bindings requires more than the traditional stack-based techniques. This paper provides correctness criteria for such dynamic environments, along with contrasting implementations. A store semantics provides the framework for our correctness criteria and presentation of deepand shallow-binding implementations. The latter ...

It is well documented that reading strategies of low-literacy readers are suboptimal when text requires deeper levels of comprehension. Deep comprehension demands causal or goal-oriented reasoning and functional conceptual knowledge. Alternatively, shallow comprehension entails recall of definitions or text features without necessitating a coherent understanding of the text. The Center for Adul...

We present an approach where two different models (Deep and Shallow) are trained separately on the data and a weighted average of the outputs is taken as the final result. For the Deep approach, we use different combinations of models like Convolution Neural Network, pretrained word2vec embeddings and LSTMs to get representations which are then used to train a Deep Neural Network. For Clarity p...

We describe basic concepts and software architectures for the integration of shallow and deep (linguistics-based, semantics-oriented) natural language processing (NLP) components. The main goal of this novel, hybrid integration paradigm is improving robustness of deep processing. After an introduction to constraint-based natural language parsing, we give an overview of typical shallow processin...

Rice bran application just after transplanting has been increasingly practiced as a herbicide-substitute for organic rice production in Korea. However, this practice is frequently reported to be unsatisfactory in weed suppression. An experiment with five treatments that combine flooding depth (shallow and deep), rice bran application level (low and high), and herbicide application was carried o...