This file contains mappings from abbreviations and some acronyms to full forms for text-to-speech purposes. This is a supplement to the analyser; the analyser must tag the strings as +ABBR or similar for the transcriptions to work. The resulting full form must be lemmas known to the analyser, for further processing.

We describe here how abbreviations in No linguistic content are read out, for text-to-speech systems.

The file contains:

• miscellaneous symbols

• smileys

• Clause boundary symbols

• Single punctuation marks

• Paired punctuation marks

---

This (part of) documentation was generated from src/fst/transcriptions/transcriptor-symbols2text.lexc