Table 3
Unknown word model features for Arabic and French.
| Arabic Lexical Features | French Lexical Features |
|---|---|
▹ Presence of the determiner  | ▹ Nominal, adjectival, verbal, adverbial, and plural suffixes |
| ▹ Contains digits or punctuation | ▹ Contains digits or punctuation |
▹ Ends with the feminine affix  ah | ▹ Is capitalized (except the first word in a sentence), or consists entirely of capital letters |
▹ Various verbal (e.g.,  t,  waa,  uun) and adjectival suffixes (e.g.,  iiah,  ii) | ▹ If none of the above, deterministically extract one- and two-character suffixes |
| Arabic Lexical Features | French Lexical Features |
|---|---|
| ▹ Presence of the determiner | ▹ Nominal, adjectival, verbal, adverbial, and plural suffixes |
| ▹ Contains digits or punctuation | ▹ Contains digits or punctuation |
| ▹ Ends with the feminine affix ah | ▹ Is capitalized (except the first word in a sentence), or consists entirely of capital letters |
| ▹ Various verbal (e.g., t, waa, uun) and adjectival suffixes (e.g., iiah, ii) | ▹ If none of the above, deterministically extract one- and two-character suffixes |