斯坦福NLP CS224N Winter 2024 作业：Assignment 1

原始题目
https://web.stanford.edu/class/cs224n/assignments/a1_preview/exploring_word_vectors.html

Question 1.1: Implement distinct_words [code] (2 points)

输入：
· corpus: 包括多个句子的语料

输出

• corpus_words: 先去重，再排序后的单词列表
• num_corpus_words：去重重复后的单词数量

def distinct_words(corpus):
    """ Determine a list of distinct words for the corpus.
        Params:
            corpus (list of list of strings): corpus of documents
        Return:
            corpus_words (list of strings): sorted list of distinct words across the corpus
            n_corpus_words (integer): number of distinct words across the corpus
    """
    corpus_words = []
    n_corpus_words = -1
    
    # ------------------
    # Write your implementation here.
    distinct_words_set  = set()
    for sentence in corpus:
        distinct_words_set.update(sentence )

    corpus_words = sorted(list(distinct_words_set))
    num_corpus_words = len(corpus_words)
   
    # ------------------

    return corpus_words, num_corpus_words
    ``
    # Question 1.2: Implement compute_co_occurrence_matrix [code] (3 points)