arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2104.08787cs.CL
收藏

基于交叉注意的汉语句子相似度研究

Chinese Sentences Similarity via Cross-Attention Based Siamese Network

Delft University of Technology(代尔夫特理工大学)

Zhen Wang, Xiangxie Zhang, Yicong Tan

摘要:

测量句子相似性是当今的一个关键研究领域,因为它可以让机器更好地理解人类语言。本文提出了一种交叉注意连体网络(CATsNet)来完成汉语句子语义学习和句子相似度比较的任务。这种新的模型能够捕捉非局部特征。此外,我们还尝试在模型中应用长短期记忆(LSTM)网络来提高其性能。在LCQMC数据集上进行了实验,结果表明,我们的模型可以达到更高的精度比以前的工作。

英文摘要:

Measuring sentence similarity is a key research area nowadays as it allows machines to better understand human languages. In this paper, we proposed a Cross-Attention Siamese Network (CATsNet) to carry out the task of learning the semantic meanings of Chinese sentences and comparing the similarity between two sentences. This novel model is capable of catching non-local features. Additionally, we also tried to apply the long short-term memory (LSTM) network in the model to improve its performance. The experiments were conducted on the LCQMC dataset and the results showed that our model could achieve a higher accuracy than previous work.

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。

↑