用于阿拉伯语隐式方面识别的特定语言与跨语言知识图谱：推理和适应策略的比较研究
Language-Specific versus Cross-Lingual Knowledge Graphs for Implicit Aspect Identification in Arabic: A Comparative Study of Reasoning and Adaptation Strategies
浏览论文内容
中文总结 AI 辅助
研究阿拉伯语隐式方面识别中特定语言与跨语言知识图谱策略，在混合管道中比较两种策略及生成提取器的零样本提示和特定任务微调两种适应策略，发现阿拉伯语本地KG效果更好，特定任务微调提升显著。
中文摘要 AI 辅助
阿拉伯语的基于方面的情感分析（ABSA）必须找出文本中明确提及的方面和从未提及的隐式方面。隐式识别通常依赖将观点线索与方面类别联系起来的辅助知识源（如知识图谱（KG）），但对于资源较少的语言，从业者面临设计选择：通过多语言嵌入重用成熟的英语KG，或构建较小的阿拉伯语本地KG。本文在一个混合管道中对这两种策略进行了对照比较，并在三个阿拉伯语基准上进行了评估。我们还比较了为KG提供信息的生成提取器的两种适应策略——零样本提示与针对具有8B参数的大语言模型（LLM）的特定任务微调。阿拉伯语本地KG（策略2）在M-ABSA上的微F1得分比跨语言英语KG（策略1）高+0.199，在SemEval-2016上高+0.251，在精确率和召回率上均有所提高。特定任务微调将M-ABSA和SemEval-2016上的显式提取微F1得分从<=0.13（零样本）提高到0.66-0.76（在较小的HAAD上为0.45），证实了在形态丰富的语言中，任务适应而非模型规模起决定性作用。
英文摘要
Aspect-based sentiment analysis (ABSA) in Arabic must recover both explicitly stated aspects and implicit aspects that are never named in the text. Implicit identification typically relies on an auxiliary knowledge source (e.g., a knowledge graph (KG)) linking opinion cues to aspect categories, but for a lower-resource language the practitioner faces a design choice: reuse a mature English KG through multilingual embeddings, or build a smaller native Arabic KG. This paper reports a controlled comparison of the two strategies within a single hybrid pipeline, evaluated on three Arabic benchmarks (M-ABSA, SemEval-2016 Arabic, and HAAD). We further compare two adaptation strategies for the generative extractor that feeds the KG -- zero-shot prompting versus task-specific fine-tuning of an 8B-parameter large language model (LLM). The native Arabic KG (Strategy 2) outperforms the cross-lingual English KG (Strategy 1) by +0.199 micro-F1 on M-ABSA and +0.251 on SemEval-2016, gaining on both precision and recall. Task-specific fine-tuning raises explicit-extraction micro-F1 from <= 0.13 (zero-shot) to 0.66-0.76 on M-ABSA and SemEval-2016 (0.45 on the smaller HAAD), confirming that task adaptation, rather than model scale, is decisive in a morphologically rich language.
发表机构
- Saudi Electronic University（沙特电子大学）
机构由 AI 辅助整理，请以论文原文为准。
