arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1607.02061cs.CLcs.AI
收藏

用丰富的语境表示动词:对动词相似性的评价

Representing Verbs with Rich Contexts: an Evaluation on Verb Similarity

Aix-Marseille University(艾克斯-马赛大学);The Hong Kong Polytechnic University(香港理工大学);University of Pisa(比萨大学)

Emmanuele Chersoni, Enrico Santus, Alessandro Lenci, Philippe Blache, Chu-Ren Huang

摘要:

一些关于句子加工的研究表明,心理词汇记录了单词之间的相互期望。然而,目前的DSM将上下文单词表示为单独的特征,从而丢失了单词期望的重要信息,例如单词相互关系。在本文中,我们提出了一个DSM,解决这个问题,定义动词上下文作为联合句法依赖。我们在两个数据集上的动词相似性任务中测试了我们的表示,表明联合上下文实现了与单个依赖项相当甚至更好的性能。此外,他们能够克服联合特征空间的数据稀疏性问题,尽管我们的训练语料库的大小有限。

英文摘要:

Several studies on sentence processing suggest that the mental lexicon keeps track of the mutual expectations between words. Current DSMs, however, represent context words as separate features, thereby loosing important information for word expectations, such as word interrelations. In this paper, we present a DSM that addresses this issue by defining verb contexts as joint syntactic dependencies. We test our representation in a verb similarity task on two datasets, showing that joint contexts achieve performances comparable to single dependencies or even better. Moreover, they are able to overcome the data sparsity problem of joint feature spaces, in spite of the limited size of our training corpus.

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。

↑