对比三类轻量Transformer模型，为企业NLP部署提供实证选型参考
Comparative Efficiency Analysis of Lightweight Transformer Models: A Multi-Domain Empirical Benchmark for Enterprise NLP Deployment
- 在多领域任务中对比DistilBERT、MiniLM、ALBERT的性能与效率
- MiniLM推理最快、吞吐最高，ALBERT准确率领先，DistilBERT最均衡
- 结果适用于企业级场景，指导低延迟或资源受限环境的模型选择
在企业自然语言处理快速发展的背景下，对能够处理多领域文本自动化任务的高效轻量级模型需求日益迫切。本研究在客户情绪分类、新闻主题分类和仇恨言论检测三个不同领域，对比了三种主流轻量级Transformer模型——DistilBERT、MiniLM和ALBERT。基于IMDB、AG News和Measuring Hate Speech数据集，评估了准确率、精确率、召回率、F1分数等精度指标，以及模型大小、推理时间、吞吐量和内存占用等效率指标。关键发现表明，无单一模型在所有维度占优：ALBERT在多个任务中取得最高任务特定准确率，MiniLM在推理速度和吞吐量上表现最佳，DistilBERT则在各类任务中保持最稳定的准确率并具备竞争力的效率。所有结果均在固定企业约束下进行可控微调，未进行穷尽式超参数优化。研究揭示了准确率与效率之间的权衡，建议将MiniLM用于低延迟敏感应用，DistilBERT用于平衡性能场景，ALBERT用于资源受限环境。
原文摘要 · Abstract (English)
In the rapidly evolving landscape of enterprise natural language processing (NLP), the demand for efficient, lightweight models capable of handling multi-domain text automation tasks has intensified. This study conducts a comparative analysis of three prominent lightweight Transformer models - DistilBERT, MiniLM, and ALBERT - across three distinct domains: customer sentiment classification, news topic classification, and toxicity and hate speech detection. Utilizing datasets from IMDB, AG News, and the Measuring Hate Speech corpus, we evaluated performance using accuracy-based metrics including accuracy, precision, recall, and F1-score, as well as efficiency metrics such as model size, inference time, throughput, and memory usage. Key findings reveal that no single model dominates all performance dimensions. ALBERT achieves the highest task-specific accuracy in multiple domains, MiniLM excels in inference speed and throughput, and DistilBERT demonstrates the most consistent accuracy across tasks while maintaining competitive efficiency. All results reflect controlled fine-tuning under fixed enterprise-oriented constraints rather than exhaustive hyperparameter optimization. These results highlight trade-offs between accuracy and efficiency, recommending MiniLM for latency-sensitive enterprise applications, DistilBERT for balanced performance, and ALBERT for resource-constrained environments.
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。