Тор

We present Minimum Bayes-Risk (MBR) de- coding over translation lattices that compactly encode a huge number of translation hypothe- ses. We describe conditions on the loss func- tion that will …...

We report results on translation of SMS mes- sages from Haitian Creole to English. We show improvements by applying spell check- ing techniques to unknown words and creating a lattice …...

Efficient computation of n-gram posterior probabilities from lattices has applications in lattice-based minimum Bayes-risk de- coding in statistical machine translation and the estimation of expected document frequencies from spoken corpora. …...

AbstractLattices are an efficient and effective method to encode ambiguity of upstream systems in natural language processing tasks, for example to compactly capture multiple speech recognition hypotheses, or to represent …...

AbstractIncorporating lexicons into character-level Chinese NER by lattices is proven effective to exploitrich word boundary information. Previous work has extended RNNs to consume lattice inputsand achieved great success. However, due …...

AbstractConditional neural text generation models generate high-quality outputs, but often concentrate around a mode when what we really want is a diverse set of options. We present a search algorithm …...

AbstractDeciphering historical substitution ciphers is a challenging problem. Example problems that have been previously studied include detecting cipher type, detecting plaintext language, and acquiring the substitution key for segmented ciphers. …...