Select Language

AI社区

公开数据集

Chinese Word Analogy Lists 汉语词语类比数据集

Chinese Word Analogy Lists 汉语词语类比数据集

121.1M
442 浏览
0 喜欢
0 次下载
0 条讨论
MNIST Classification

Most word embedding methods take a word as a basic unit and learn embeddings according to words’ external contexts, ign......

数据结构 ? 121.1M

    Data Structure ?

    * 以上分析是由系统提取分析形成的结果,具体实际数据为准。

    README.md

    Most word embedding methods take a word as a basic unit and learn embeddings according to words’ external contexts, ignoring the internal structures of words. However, in some languages such as Chinese, a word is usually composed of several characters and contains rich internal information. The semantic meaning of a word is also related to the meanings of its composing characters. Hence, we take Chinese for example, and present a character-enhanced word embedding model (CWE). In order to address the issues of character ambiguity and non-compositional words, we propose multiple-prototype character embeddings and an effective word selection method. We evaluate the effectiveness of CWE on word relatedness computation and analogical reasoning. The results show that CWE outperforms other baseline methods which ignore internal character information.

    The work is published in IJCAI 2015, entitled with "Joint Learning of Character and Word Embeddings". This project maintains the source codes and evaluation data for character-enhanced word embedding model (CWE). The analogical reasoning dataset on Chinese is available in data folder. Hope the codes and data are helpful for your research in NLP. If you use the codes or the data, please cite this paper:

    Xinxiong Chen, Lei Xu, Zhiyuan Liu, Maosong Sun, Huanbo Luan. Joint Learning of Character and Word Embeddings. The 25th International Joint Conference on Artificial Intelligence (IJCAI 2015).

    Download paper:http://nlp.csai.tsinghua.edu.cn/~lzy/publications/ijcai2015_character.pdf

    Note

    The CWE project (MIT license) is based on Google's word2vec project (Apache 2.0 License).

    by Leonard Xu

    leonard.xu.thu@gmail.com


    ×

    帕依提提提温馨提示

    该数据集正在整理中,为您准备了其他渠道,请您使用

    注:部分数据正在处理中,未能直接提供下载,还请大家理解和支持。
    暂无相关内容。
    暂无相关内容。
    • 分享你的想法
    去分享你的想法~~

    全部内容

      欢迎交流分享
      开始分享您的观点和意见,和大家一起交流分享.
    所需积分:4 去赚积分?
    • 442浏览
    • 0下载
    • 0点赞
    • 收藏
    • 分享