arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1806.04713cs.CL
收藏

无监督组合表示的评估

Evaluation of Unsupervised Compositional Representations

The George Washington University(乔治华盛顿大学)

Hanan Aldarmaki, Mona Diab

摘要:

我们在几个外部监督和无监督评估基准上评估了各种组合模型,从词袋表示到基于RNN的组合模型。我们的研究结果证实,加权向量平均在大多数基准测试中的表现优于上下文敏感模型,但RNN模型中编码的结构特征在某些分类任务中也很有用。我们分析了一些评估数据集,以确定它们测量的意义方面以及解释其性能差异的各种模型的特征。

英文摘要:

We evaluated various compositional models, from bag-of-words representations to compositional RNN-based models, on several extrinsic supervised and unsupervised evaluation benchmarks. Our results confirm that weighted vector averaging can outperform context-sensitive models in most benchmarks, but structural features encoded in RNN models can also be useful in certain classification tasks. We analyzed some of the evaluation datasets to identify the aspects of meaning they measure and the characteristics of the various models that explain their performance variance.

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。

↑