arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1904.01451cs.CLcs.LG
收藏

使用多意义向量嵌入实现反向词典

Using Multi-Sense Vector Embeddings for Reverse Dictionaries

Saarland Informatics Campus(萨尔兰信息学园区);Max Planck Institute for Informatics(马克斯·普朗克信息学研究所);Rutgers University(罗格斯大学)

Michael A. Hedderich, Andrew Yates, Dietrich Klakow, Gerard de Melo

摘要:

流行的词嵌入方法,如word2vec和GloVe,为每个词分配一个向量表示,即使一个词有多个不同的含义。相反,多意义嵌入为单词的每个意义提供不同的向量。然而,它们通常不能作为传统单义嵌入的替代品,因为需要为每个单词选择正确的意义向量。在这项工作中,我们研究的效果,多意义嵌入的任务,反向字典。我们提出了一种技术,可以很容易地将它们集成到现有的神经网络架构使用注意力机制。我们的实验表明,大的改进时,可以获得多意义嵌入在输入序列以及目标表示。分析的意义分布和学习的注意力。

英文摘要:

Popular word embedding methods such as word2vec and GloVe assign a single vector representation to each word, even if a word has multiple distinct meanings. Multi-sense embeddings instead provide different vectors for each sense of a word. However, they typically cannot serve as a drop-in replacement for conventional single-sense embeddings, because the correct sense vector needs to be selected for each word. In this work, we study the effect of multi-sense embeddings on the task of reverse dictionaries. We propose a technique to easily integrate them into an existing neural network architecture using an attention mechanism. Our experiments demonstrate that large improvements can be obtained when employing multi-sense embeddings both in the input sequence as well as for the target representation. An analysis of the sense distributions and of the learned attention is provided as well.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑