Data scarcity is one of the main obstacles of domain adaptation in spoken language understanding (SLU) due to the high cost of creating manually tagged SLU datasets. Recent works in neural text generative models, particularly latent variable models such as variational autoencoder (VAE), have shown promising results in regards to generating plausible and natural sentences. In this paper, we propose a novel generative architecture which leverages the generative power of latent variable models to jointly synthesize fully annotated utterances. Our experiments show that existing SLU models trained on the additional synthetic examples achieve performance gains. Our approach not only helps alleviate the data scarcity issue in the SLU task for many datasets but also indiscriminately improves language understanding performances for various SLU models, supported by extensive experiments and rigorous statistical testing.

Scratch and App Inventor are two of the most widely used block-based programming languages for young students. These are educational languages which allow students to program easily by dragging and dropping their code blocks. One question that arises in relation to these educational languages is which of them would be more helpful in fostering computational thinking. It is difficult to answer this question because each language has its own advantages. In this paper, we propose a novel rubric based on Dr. Scratch for assessing both Scratch and App Inventor projects in terms of computational thinking concept learning. We crawled teachers’ and students’ open and popular projects and automatically calculated their effectiveness scores with regard to learning computational thinking concepts based on our rubric. The experimental results show that (1) Scratch projects scored higher on average in Parallelism, Synchronization and Flow Control, while App Inventor projects scored higher on average in User Interactivity and Data Representation. The results also show that (2) in many cases, large programs with numerous lines of code scored high in all areas of computational thinking concepts.

We introduce a novel approach that jointly learns slot filling and delexicalized sentence generation. There have been recent attempts to tackle slot filling as a type of sequence labeling problem, with encoder-decoder attention framework. We further improve the framework by training the model to generate delexicalized sentences, in which words according to slot values are replaced with slot labels. Slot filling with delexicalization shows better results compared to models having a single learning objective of filling slots. The proposed method achieves state-of-the-art slot filling performance on ATIS dataset. We experiment different variants of our model and find that delexicalization encourages generalization by sharing weights among the words with same labels and helps the model to further leverage certain linguistic features.

No abstract

No abstract