wordmap/dist/Parser.d.ts

Multi-Lingual Word Alignment Prediction

import { Token } from "wordmap-lexer";
import PermutationIndex from "./index/PermutationIndex";
import Alignment from "./structures/Alignment";
import Ngram from "./structures/Ngram";
/**
 * A collection of parsing functions
 */
export default class Parser {
    /**
     * Returns an array of n-grams of a particular size from a sentence
     * @param {Array<Token>} sentence - the sentence from which n-grams will be read
     * @param {number} ngramLength - the length of each n-gram.
     * @returns {Array<Ngram>}
     */
    static sizedNgrams(sentence: Token[], ngramLength: number): Ngram[];
    /**
     * Generates an array of all possible contiguous n-grams within the sentence.
     * @param {Array<Token>} sentence - the tokens in a sentence
     * @param {number} [maxNgramLength=3] - the maximum n-gram size to generate
     * @returns {any[]}
     */
    static ngrams(sentence: Token[], maxNgramLength?: number): Ngram[];
    /**
     * Generates an array of all possible alignments between two sets of n-grams
     * @deprecated used {@link indexAlignmentPermutations} instead (it's faster).
     * @param {Ngram[]} sourceNgrams - every possible n-gram in the source text
     * @param {Ngram[]} targetNgrams - every possible n-gram in the target text
     * @return {Alignment[]}
     */
    static alignments(sourceNgrams: Ngram[], targetNgrams: Ngram[]): Alignment[];
    /**
     * Indexes all possible alignment permutations between two sets of n-grams
     * @param {Ngram[]} sourceNgrams - every possible n-gram in the source text
     * @param {Ngram[]} targetNgrams - every possible n-gram in the target text
     * @param {PermutationIndex} index - the index that will receive the permutations
     */
    static indexAlignmentPermutations(sourceNgrams: Ngram[], targetNgrams: Ngram[], index: PermutationIndex): void;
}