We demonstrate the effectiveness of multilingual learning for unsupervised part-of-speech tagging. The key hypothesis of multilingual learning is that by combining cues from multi...
Benjamin Snyder, Tahira Naseem, Jacob Eisenstein, ...
Abstract. We describe compiler and run-time optimisations for effective autoparallelisation of C++ programs on the Cell BE architecture. Auto-parallelisation is made easier by anno...
Most current XQuery implementations require that all XML data reside in memory in one form or another before they start processing the data. This is unacceptable for large XML doc...
Automatically extracting semantic content from audio streams can be helpful in many multimedia applications. Motivated by the known limitations of traditional supervised approache...
Situational awareness (SA) applications monitor the real world and the entities therein to support tasks such as rapid decision making, reasoning, and analysis. Raw input about unf...