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 2402.10772cs.CL
收藏

通过早期融合和多语言模型增强ESG影响类型识别

Enhancing ESG Impact Type Identification through Early Fusion and Multilingual Models

UCLA(加利福尼亚大学洛杉矶分校);Virginia Tech(弗吉尼亚理工大学)

Hariram Veeramani, Surendrabikram Thapa, Usman Naseem

AI总结:

本研究针对ML-ESG-2任务中ESG影响类型识别问题,提出结合早期与晚期融合的集成学习系统,利用mBERT、FlauBERT、ALBERT及含LSA和TF-IDF特征的MLP模型,发现早期融合集成方法性能最佳,助力可持续决策。

摘要:

在环境、社会与公司治理(ESG)影响评估不断演变的背景下,ML-ESG-2共享任务提出了识别ESG影响类型的目标。为应对这一挑战,我们提出了一套利用集成学习技术的综合系统,结合了早期与晚期融合方法。我们的方法采用了四种不同的模型:mBERT、FlauBERT-base、ALBERT-base-v2,以及一个结合了潜在语义分析(LSA)和词频-逆文档频率(TF-IDF)特征的多层感知机(MLP)。通过大量实验,我们发现采用早期融合集成方法(集成了LSA、TF-IDF、mBERT、FlauBERT-base和ALBERT-base-v2)取得了最佳性能。我们的系统提供了全面的ESG影响类型识别解决方案,有助于当今金融与公司治理领域至关重要的负责任和可持续决策过程。

英文摘要:

In the evolving landscape of Environmental, Social, and Corporate Governance (ESG) impact assessment, the ML-ESG-2 shared task proposes identifying ESG impact types. To address this challenge, we present a comprehensive system leveraging ensemble learning techniques, capitalizing on early and late fusion approaches. Our approach employs four distinct models: mBERT, FlauBERT-base, ALBERT-base-v2, and a Multi-Layer Perceptron (MLP) incorporating Latent Semantic Analysis (LSA) and Term Frequency-Inverse Document Frequency (TF-IDF) features. Through extensive experimentation, we find that our early fusion ensemble approach, featuring the integration of LSA, TF-IDF, mBERT, FlauBERT-base, and ALBERT-base-v2, delivers the best performance. Our system offers a comprehensive ESG impact type identification solution, contributing to the responsible and sustainable decision-making processes vital in today's financial and corporate governance landscape.

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。

↑