Learn More
We are applying a memory based learning (MBL) algorithm to the task of automatic dialog act (DA) tagging. This work is along the lines of a recent trend that considers MBL as being more appropriate for natural language processing. We did the experiments on the Switchboard corpus, overcome the problem of feature selection and yield results that seem to be(More)
This paper presents a strategy for testing future generations of wafer-level packaged logic devices that have nanoscale I/O structures. The strategy assumes that the devices incorporate built-in self test (BIST) features so that only a subset of the functional I/O needs to be directly accessed during testing. A miniature tester is described that provides(More)
Many practical information extraction systems use simple taxonomies for mapping extracted strings to client-specific concept codes. In such taxonomies, concepts are defined as groups of semantically similar words and phrases. For the mapping to be accurate, a new client-specific taxonomy – usually nothing more than a set of concept codes, each with a single(More)
This paper presents a deep architecture for learning a similarity metric on variable-length character sequences. The model combines a stack of character-level bidi-rectional LSTM's with a Siamese architecture. It learns to project variable-length strings into a fixed-dimensional embedding space by using only information about the similarity between pairs of(More)
We study dependencies between discourse structure and speech recognition problems (SRP) in a corpus of speech-based computer tutoring dialogues. This analysis can inform us whether there are places in the discourse structure prone to more SRP. We automatically extract the discourse structure by taking advantage of how the tutoring information is encoded in(More)