arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.16700cs.CLcs.AI
收藏

为情感分析生成有效的集成模型

Generating Effective Ensembles for Sentiment Analysis

Bar-Ilan University(巴伊兰大学);Jerusalem College of Technology(耶路撒冷理工学院);AI-Weinberg, AI Experts(AI-Weinberg人工智能专家机构)

Itay Etelis, Avi Rosenfeld, Abraham Itzhak Weinberg, David Sarne

AI总结:

本文提出分层集成构建算法 HEC,将 transformer 与传统 NLP 模型混合集成,在八个情感分析数据集上显著超越传统集成方法,并优于 GPT-4。

摘要:

近年来,transformer 模型彻底改变了自然语言处理(NLP),在包括情感分析(SA)在内的各种任务中取得了卓越成果。因此,当前最先进的情感分析方法主要仅依赖 transformer 模型,在基准数据集上达到了令人印象深刻的准确率。在本文中,我们表明,进一步提高此类情感分析集成模型准确率的关键在于不仅要纳入 transformer,还要纳入传统的 NLP 模型,尽管后者相较于 transformer 模型表现较差。然而,正如我们通过实验所展示的,这需要改变集成模型的构建方式,具体来说,需要依赖我们提出的分层集成构建(Hierarchical Ensemble Construction,HEC)算法。我们在八个典型情感分析数据集上的实证研究表明,纳入混合模型类型并通过 HEC 构建的集成模型显著优于传统集成模型。最后,我们对 HEC 与 GPT-4 的性能进行了比较分析,结果表明,尽管 GPT-4 已接近最先进的情感分析方法,但其性能仍不如我们提出的集成策略。

英文摘要:

In recent years, transformer models have revolutionized Natural Language Processing (NLP), achieving exceptional results across various tasks, including Sentiment Analysis (SA). As such, current state-of-the-art approaches for SA predominantly rely on transformer models alone, achieving impressive accuracy levels on benchmark datasets. In this paper, we show that the key for further improving the accuracy of such ensembles for SA is to include not only transformers, but also traditional NLP models, despite the inferiority of the latter compared to transformer models. However, as we empirically show, this necessitates a change in how the ensemble is constructed, specifically relying on the Hierarchical Ensemble Construction (HEC) algorithm we present. Our empirical studies across eight canonical SA datasets reveal that ensembles incorporating a mix of model types, structured via HEC, significantly outperform traditional ensembles. Finally, we provide a comparative analysis of the performance of the HEC and GPT-4, demonstrating that while GPT-4 closely approaches state-of-the-art SA methods, it remains outperformed by our proposed ensemble strategy.

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。

↑