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 1709.01186cs.CL
收藏

学习神经词汇显著性分数

Learning Neural Word Salience Scores

University of Liverpool(利物浦大学);Science and Technology Facilities Council(科学技术设施委员会)

Krasen Samardzhiev, Andrew Gargett, Danushka Bollegala

摘要:

测量一个词的显著性是许多NLP任务中必不可少的步骤。启发式的方法,如tfidf已被用于迄今估计的显着性的话。我们建议\emph{Neural Word Salience}(NWS)的分数,不像统计学,是从语料库中学习。具体来说,我们学习单词显著性分数,以便使用预先训练的词嵌入作为输入,可以准确地预测出现在句子中的单词,给定出现在该句子之前或之后的句子中的单词。句子相似性预测的实验结果表明,学习的单词显着性分数执行三倍或更好的一些国家的最先进的方法来表示句子的基准数据集上的句子相似性,而只使用一小部分的训练和预测时间所需的现有方法。此外,我们的NWS分数正相关的心理语言学措施,如具体性,和imagerity意味着一个密切的联系,由人类感知的显着性。

英文摘要:

Measuring the salience of a word is an essential step in numerous NLP tasks. Heuristic approaches such as tfidf have been used so far to estimate the salience of words. We propose \emph{Neural Word Salience} (NWS) scores, unlike heuristics, are learnt from a corpus. Specifically, we learn word salience scores such that, using pre-trained word embeddings as the input, can accurately predict the words that appear in a sentence, given the words that appear in the sentences preceding or succeeding that sentence. Experimental results on sentence similarity prediction show that the learnt word salience scores perform comparably or better than some of the state-of-the-art approaches for representing sentences on benchmark datasets for sentence similarity, while using only a fraction of the training and prediction times required by prior methods. Moreover, our NWS scores positively correlate with psycholinguistic measures such as concreteness, and imageability implying a close connection to the salience as perceived by humans.

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。

↑