Search Descriptions

Main Topics

Search Publications


author

title

other

year

Truecasing

Within translation models, it is common to drop distinctions between surface forms of words that occur at the beginning of sentences (The), in the middle of sentences (the) or in all-caps headlines (THE). This require a pre-processing step of normalizing case and a post-processing step of generating the proper surface forms.

Truecasing is the main subject of 3 publications.

Publications

Truecasing with an HMM is discussed by Lita et al. (2003), who mainly relies on a language model. A machine learning approach allows the integration of additional features, such as properties of the source language (Wang et al., 2006).

Benchmarks

Discussion

Related Topics

New Publications

  • Munteanu and Marcu (2002)

Actions

Download

Contribute