arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.03992cs.CL
收藏

句子向量表示中的成分评估

Assessing Composition in Sentence Vector Representations

University of Maryland(马里兰大学);Institute for Advanced Computer Studies(高级计算机研究所)

Allyson Ettinger, Ahmed Elgohary, Colin Phillips, Philip Resnik

摘要:

实现语言理解的一个重要组成部分是掌握句子含义的组成,但解决这个问题的直接挑战是当前神经句子组成模型产生的句子向量表示的不透明性。我们提出了一种方法来解决这一挑战,开发任务,直接针对组成意义信息的句子向量表示具有高度的精度和控制。为了使这些受控任务的创建,我们引入了一个专门的句子生成系统,产生大的,注释的句子集满足指定的句法,语义和词汇的限制。我们描述的方法和生成系统的细节,然后提出的实验结果,应用我们的方法来探测从一些现有的句子组成模型的嵌入成分信息。我们发现,该方法是能够提取有用的信息,这些模型的不同能力,我们讨论了我们的结果的影响,这些系统的捕获句子信息。我们提供用于这些实验的数据集以及生成系统供公众使用。

英文摘要:

An important component of achieving language understanding is mastering the composition of sentence meaning, but an immediate challenge to solving this problem is the opacity of sentence vector representations produced by current neural sentence composition models. We present a method to address this challenge, developing tasks that directly target compositional meaning information in sentence vector representations with a high degree of precision and control. To enable the creation of these controlled tasks, we introduce a specialized sentence generation system that produces large, annotated sentence sets meeting specified syntactic, semantic and lexical constraints. We describe the details of the method and generation system, and then present results of experiments applying our method to probe for compositional information in embeddings from a number of existing sentence composition models. We find that the method is able to extract useful information about the differing capacities of these models, and we discuss the implications of our results with respect to these systems' capturing of sentence information. We make available for public use the datasets used for these experiments, as well as the generation system.

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。

↑