We propose a language-independent datadriven method to exhaustively extract bursty phrases of arbitrary forms (e.g., phrases other than simple noun phrases) from microblogs. The burst (i.e., the rapid increase of the occurrence) of a phrase causes the burst of overlapping Ngrams including incomplete ones. In other words, bursty incomplete N-grams inevitably overlap bursty phrases. Thus, the pro...

Standard SMT decoders operate by translating disjoint spans of input words, thus discarding information in form of overlapping phrases that is present at phrase extraction time. The use of overlapping phrases in translation may enhance fluency in positions that would otherwise be phrase boundaries, they may provide additional statistical support for long and rare phrases, and they may generate ...

Phrases Clumped 0.62 high spectral resolution 0.56 sea surface temperature S 0.39 emissivity Abstract Phrases Clumped -0.54 full Landsat Thematic Map -0.52 land cover -0.44 Synthetic Aperture Radar -0.43 data sets -0.38 classifications Abstract Phrases Clumped -0.68 High Resolution Radiomete -0.50 difference vegetation ind -0.44 real time -0.38 satellite data Abstract Phrases Clumped -0.59 radi...

Cue-Based Dialogue Act Classification Nick Webb Supervisors: Yorick Wilks & Mark Hepple In this thesis, we will address three research questions relating to the discovery and use of cue phrases for Dialogue Act classification. Cue phrases are single words, or combinations of words in phrases, that can serve as reliable indicators of some discourse function. In our case, we are looking to automa...