arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1412.2197cs.CL
收藏

大规模同义词抽取的实践

Practice in Synonym Extraction at Large Scale

Liangliang Cao, Chang Wang

摘要:

同义词抽取是自然语言处理中的一项重要任务,常作为查询扩展、问答等应用中的子模块。自动同义词提取器是大规模应用的首选。以往的同义词抽取研究大多局限于小规模数据集。在本文中,我们构建了一个包含340万个同义词/非同义词对的大型数据集,以捕捉现实世界中的挑战。我们提出了(1)一个新的成本函数来适应不平衡学习问题,以及(2)一个基于特征学习的深度神经网络来建模同义词对中的复杂关系。比较了几种基于支持向量机和神经网络的方法,发现一种新的基于特征学习的神经网络方法优于手工分配特征的方法。具体来说,我们的模型的最佳性能超过了SVM基线,具有显着的97%的相对改善。

英文摘要:

Synonym extraction is an important task in natural language processing and often used as a submodule in query expansion, question answering and other applications. Automatic synonym extractor is highly preferred for large scale applications. Previous studies in synonym extraction are most limited to small scale datasets. In this paper, we build a large dataset with 3.4 million synonym/non-synonym pairs to capture the challenges in real world scenarios. We proposed (1) a new cost function to accommodate the unbalanced learning problem, and (2) a feature learning based deep neural network to model the complicated relationships in synonym pairs. We compare several different approaches based on SVMs and neural networks, and find out a novel feature learning based neural network outperforms the methods with hand-assigned features. Specifically, the best performance of our model surpasses the SVM baseline with a significant 97\% relative improvement.

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。

↑