Language models for speech recognition tend to be brittle across domains, since their performance is vulnerable to changes in the genre or topic of the text on which they are trai...
The Semantic Web seems to be evolving into a property-linked web of RDF data, conceptually divorced from (but physically housed in) the hyperlinked web of HTML documents. We discus...
We address the problem of improving the efficiency of natural language text input under degraded conditions (for instance, on mobile computing devices or by disabled users), by ta...
On the Internet, users often encounter noise in the form of spelling errors or unknown words, however, dishonest, unreliable, or biased information also acts as noise that makes i...
Koji Murakami, Eric Nichols, Junta Mizuno, Yotaro ...
A Bloom filter (BF) is a randomised data structure for set membership queries. Its space requirements are significantly below lossless information-theoretic lower bounds but it ...