We propose an architecture to jointly learn word and label embeddings for slot filling in spoken language understanding. The proposed approach encodes labels using a combination of word embeddings and straightforward word-label association from the training data. Compared to the state-of-the-art methods, our approach does not require label embed-dings as part of the input and therefore lends itself nicely to a wide range of model architectures. In addition, our architecture computes contextual distances between words and labels to avoid adding contextual windows, thus reducing memory footprint. We validate the approach on established spoken dialogue datasets and show that it can achieve state-of-the-art performance with much fewer trainable parameters.

Data captured in OWL ontologies is generally considered to be more prone to changes than the schema in many situations. Such changes often necessitate consistency checking over the resulting ontologies in order to maintain coherent knowledge, specifically in dynamic settings. In this paper, we present an approach to check the consistency over an evolving ontology resulting from data insertions and deletions, given by some expressive underlying Description Logic dialect. The approach, assuming an initially consistent ontology, works by syntactically identifying "relevant" and representative parts of the data for the given updates, i.e., the part that may contribute to subsequent consistency checking. Our approach has demonstrated its efficacy in checking consistency over large and real-world ontologies and outperforms existing approaches in several circumstances.

We consider a generalization of instance retrieval over knowledge bases that provides users with assertions in which descriptions of qualifying objects are given in addition to their identifiers. Notably, this involves a transfer of basic database paradigms involving caching and query rewriting in the context of an assertion retrieval algebra. We present an optimization framework for this algebra, with a focus on finding plans that avoid any need for general knowledge base reasoning at query execution time when sufficient cached results of earlier requests exist.