arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2105.07623cs.CL
收藏

基于上下文的句子相似度研究

Sentence Similarity Based on Contexts

Chinese Academy of Sciences(中国科学院);Zhejiang University(浙江大学);Nanyang Technological University(南洋理工大学);Peking University(北京大学);Peng Cheng Laboratory(鹏城实验室);ICT(中国科学院计算技术研究所)

Xiaofei Sun, Yuxian Meng, Xiang Ao, Fei Wu, Tianwei Zhang, Jiwei Li, Chun Fan

摘要:

现有的句子相似性度量方法面临两个挑战:(1)标记数据集通常大小有限,不足以训练监督神经模型;(2)基于无监督语言建模(LM)的模型计算句子之间的语义得分存在训练-测试差距,因为句子级别的语义在训练时没有显式建模。这导致在该任务中的较差性能。在这项工作中,我们提出了一个新的框架来解决这两个问题。所提出的框架是基于这样的核心思想,即一个句子的意义应该由它的上下文来定义,并且句子相似性可以通过比较给定相同上下文的两个句子的生成概率来测量。所提出的框架能够以无监督的方式生成高质量的大规模数据集,其中两个句子之间的语义相似度得分,可以在很大程度上弥合训练测试差距。大量的实验表明,该框架实现了显着的性能提升超过现有的基线下的监督和无监督设置在不同的数据集。

英文摘要:

Existing methods to measure sentence similarity are faced with two challenges: (1) labeled datasets are usually limited in size, making them insufficient to train supervised neural models; (2) there is a training-test gap for unsupervised language modeling (LM) based models to compute semantic scores between sentences, since sentence-level semantics are not explicitly modeled at training. This results in inferior performances in this task. In this work, we propose a new framework to address these two issues. The proposed framework is based on the core idea that the meaning of a sentence should be defined by its contexts, and that sentence similarity can be measured by comparing the probabilities of generating two sentences given the same context. The proposed framework is able to generate high-quality, large-scale dataset with semantic similarity scores between two sentences in an unsupervised manner, with which the train-test gap can be largely bridged. Extensive experiments show that the proposed framework achieves significant performance boosts over existing baselines under both the supervised and unsupervised settings across different datasets.

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。

↑