Annotates the tokens with lemmata for plural nouns and conjugated verbs, where each token is a [word, part-of-speech] list.
(tokens)
| 176 | )) |
| 177 | |
| 178 | def find_lemmata(tokens): |
| 179 | """ Annotates the tokens with lemmata for plural nouns and conjugated verbs, |
| 180 | where each token is a [word, part-of-speech] list. |
| 181 | """ |
| 182 | for token in tokens: |
| 183 | word, pos, lemma = token[0], token[1], token[0] |
| 184 | if pos.startswith(("DT", "JJ")): |
| 185 | lemma = predicative(word) |
| 186 | if pos == "NNS": |
| 187 | lemma = singularize(word) |
| 188 | if pos.startswith(("VB", "MD")): |
| 189 | lemma = conjugate(word, INFINITIVE) or word |
| 190 | token.append(lemma.lower()) |
| 191 | return tokens |
| 192 | |
| 193 | class Parser(_Parser): |
| 194 |
no test coverage detected
searching dependent graphs…