arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1604.00461cs.CLcs.AIcs.LG
收藏

基于低秩张量的词汇特征嵌入

Embedding Lexical Features via Low-Rank Tensors

Harbin Institute of Technology(哈尔滨工业大学);IBM Watson(IBM沃森);Johns Hopkins University(约翰斯·霍普金斯大学);Carnegie Mellon University(卡内基梅隆大学)

Mo Yu, Mark Dredze, Raman Arora, Matthew Gormley

摘要:

现代NLP模型严重依赖工程特征,这些特征通常将单词和上下文信息组合成复杂的词汇特征。这样的组合导致大量的特征,这可能导致过拟合。我们提出了一个新的模型,表示复杂的词汇功能-包括部分的话,上下文信息和标签-在一个张量,捕捉这些部分之间的连接信息。我们将低秩张量近似应用于相应的参数张量,以减少参数空间并提高预测速度。此外,我们研究了两种方法处理功能,包括$n$ -混合长度的克。我们的模型在关系抽取、PP附加和介词消歧等任务上取得了最先进的结果。

英文摘要:

Modern NLP models rely heavily on engineered features, which often combine word and contextual information into complex lexical features. Such combination results in large numbers of features, which can lead to over-fitting. We present a new model that represents complex lexical features---comprised of parts for words, contextual information and labels---in a tensor that captures conjunction information among these parts. We apply low-rank tensor approximations to the corresponding parameter tensors to reduce the parameter space and improve prediction speed. Furthermore, we investigate two methods for handling features that include $n$-grams of mixed lengths. Our model achieves state-of-the-art results on tasks in relation extraction, PP-attachment, and preposition disambiguation.

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。

↑