特定功能词表示的多方向联想优化
Multidirectional Associative Optimization of Function-Specific Word Representations
摘要：
我们提出了一个神经框架，用于学习相关的单词组之间的关联，如发现在主谓宾（SVO）结构。我们的模型诱导了一个联合功能特定的词向量空间，例如，合理的SVO组合物的向量躺在一起。该模型即使在联合空间中也保留了关于词组成员的信息，从而可以有效地应用于SVO结构上的一些推理任务。我们显示的鲁棒性和多功能性的建议框架报告国家的最先进的结果估计选择偏好和事件相似性的任务。结果表明，使用我们的任务无关模型学习的表示组合优于先前工作中的任务特定架构，同时将参数数量减少了95%。
英文摘要：
We present a neural framework for learning associations between interrelated groups of words such as the ones found in Subject-Verb-Object (SVO) structures. Our model induces a joint function-specific word vector space, where vectors of e.g. plausible SVO compositions lie close together. The model retains information about word group membership even in the joint space, and can thereby effectively be applied to a number of tasks reasoning over the SVO structure. We show the robustness and versatility of the proposed framework by reporting state-of-the-art results on the tasks of estimating selectional preference and event similarity. The results indicate that the combinations of representations learned with our task-independent model outperform task-specific architectures from prior work, while reducing the number of parameters by up to 95%.
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。
