基于双曲图神经网络的高效环境声明检测
Efficient Environmental Claim Detection with Hyperbolic Graph Neural Networks
AI总结：
本文提出基于双曲图神经网络的环境声明检测方法，通过图结构建模实现更高效的参数使用和更高的检测性能。
摘要：
基于Transformer的模型，尤其是大型语言模型（LLMs）在NLP领域凭借其在文本生成、摘要和假新闻检测等任务中的广泛应用而占据主导地位。这些模型为大多数应用提供了易于部署和可靠性的优势，然而，它们在训练和推理过程中需要大量的计算资源，这在资源受限的应用中带来了挑战，尤其是在开源社区中，计算资源通常较为稀缺。本文提出了一种基于图的方法用于环境声明检测，探索图神经网络（GNNs）和双曲图神经网络（HGNNs）作为轻量且有效的替代方案。将任务重新定义为图分类问题，我们将声明句子转换为依赖解析图，利用词向量和可学习的词性标注（POS）嵌入作为节点特征，并在边关系中编码语法依赖。我们的实验结果表明，基于图的模型，特别是使用双曲空间（P-HGNNs）的HGNNs，在环境声明检测任务中表现出优于当前最先进方法的性能，同时参数数量减少了多达30倍。我们还展示了HGNNs在显式建模数据的层次结构（树状）结构方面受益匪浅，使它们能够显著优于欧几里得对应物。
英文摘要：
Transformer based models, especially large language models (LLMs) dominate the field of NLP with their mass adoption in tasks such as text generation, summarization and fake news detection. These models offer ease of deployment and reliability for most applications, however, they require significant amounts of computational power for training as well as inference. This poses challenges in their adoption in resource-constrained applications, especially in the open-source community where compute availability is usually scarce. This work proposes a graph-based approach for Environmental Claim Detection, exploring Graph Neural Networks (GNNs) and Hyperbolic Graph Neural Networks (HGNNs) as lightweight yet effective alternatives to transformer-based models. Re-framing the task as a graph classification problem, we transform claim sentences into dependency parsing graphs, utilizing a combination of word2vec \& learnable part-of-speech (POS) tag embeddings for the node features and encoding syntactic dependencies in the edge relations. Our results show that our graph-based models, particularly HGNNs in the poincaré space (P-HGNNs), achieve performance superior to the state-of-the-art on environmental claim detection while using up to \textbf{30x fewer parameters}. We also demonstrate that HGNNs benefit vastly from explicitly modeling data in hierarchical (tree-like) structures, enabling them to significantly improve over their euclidean counterparts.
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。
