拆解文本冲突情感，用轻量模型提升复杂语篇的分类准确率
Divide (Text) and Conquer (Sentiment): Improved Sentiment Classification by Constituent Conflict Resolution
- 将含冲突情绪的文本分块处理，分别识别各部分情感倾向
- 用小型MLP模型聚合结果，在多个数据集上超越基线模型
- 训练成本仅为微调基线的百分之一，适合资源有限场景
情感分类是自然语言处理中的复杂任务，尤其在分析包含多种矛盾语气的段落时更为困难。通常，段落越长，问题越严重，导致模型性能下降。本文提出新方法，通过分离冲突情感并有效整合，以预测整体情感。其中一种聚合策略采用多层感知机（MLP）模型，在Amazon、Twitter和SST等多个数据集上表现优于基线模型，且训练成本仅为微调基线模型的约1/100。
原文摘要 · Abstract (English)
Sentiment classification, a complex task in natural language processing, becomes even more challenging when analyzing passages with multiple conflicting tones. Typically, longer passages exacerbate this issue, leading to decreased model performance. The aim of this paper is to introduce novel methodologies for isolating conflicting sentiments and aggregating them to effectively predict the overall sentiment of such passages. One of the aggregation strategies involves a Multi-Layer Perceptron (MLP) model which outperforms baseline models across various datasets, including Amazon, Twitter, and SST while costing $\sim$1/100 of what fine-tuning the baseline would take.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。