يعمل العمل الحديث على تصنيف المعنويات على مستوى جانب الجساب شبكات اتصالا بيانيا (GCN) على أشجار التبعية لتعلم التفاعلات بين شروط الارتفاع وكلمات الرأي. في بعض الحالات، لا يمكن الوصول إلى كلمات الرأي المقابلة لمصطلح الجانب داخل القفزتين على أشجار التبعية، والتي تتطلب المزيد من طبقات GCN إلى النموذج. ومع ذلك، غالبا ما تحقق GCNS أفضل أداء بطبقتين، ولا تحقق GCNs أعمق أي مكسب إضافي. لذلك، نقوم بتصميم نماذج GCN الانتباه الانتقائية الجديدة. من ناحية، يتيح النموذج المقترح التفاعل المباشر بين شروط الجانب وكلمات السياق عن طريق عملية الانتباه الذاتي دون تحديد المسافة على أشجار التبعية. من ناحية أخرى، تم تصميم إجراء اختيار Top-K لتحديد كلمات الرأي عن طريق تحديد كلمات سياق K مع أعلى درجات الاهتمام. نقوم بإجراء تجارب على عدة مجموعات بيانات معيار شائعة الاستخدام وتظهرت النتائج أن SA-GL-GCN المقترح تفوق نماذج أساسية قوية.
Recent work on aspect-level sentiment classification has employed Graph Convolutional Networks (GCN) over dependency trees to learn interactions between aspect terms and opinion words. In some cases, the corresponding opinion words for an aspect term cannot be reached within two hops on dependency trees, which requires more GCN layers to model. However, GCNs often achieve the best performance with two layers, and deeper GCNs do not bring any additional gain. Therefore, we design a novel selective attention based GCN model. On one hand, the proposed model enables the direct interaction between aspect terms and context words via the self-attention operation without the distance limitation on dependency trees. On the other hand, a top-k selection procedure is designed to locate opinion words by selecting k context words with the highest attention scores. We conduct experiments on several commonly used benchmark datasets and the results show that our proposed SA-GCN outperforms strong baseline models.
References used
https://aclanthology.org/
Recent work on aspect-level sentiment classification has demonstrated the efficacy of incorporating syntactic structures such as dependency trees with graph neural networks (GNN), but these approaches are usually vulnerable to parsing errors. To bett
Aspect-level sentiment classification (ALSC) aims at identifying the sentiment polarity of a specified aspect in a sentence. ALSC is a practical setting in aspect-based sentiment analysis due to no opinion term labeling needed, but it fails to interp
It is popular that neural graph-based models are applied in existing aspect-based sentiment analysis (ABSA) studies for utilizing word relations through dependency parses to facilitate the task with better semantic guidance for analyzing context and
Aspect-based sentiment analysis (ABSA) typically focuses on extracting aspects and predicting their sentiments on individual sentences such as customer reviews. Recently, another kind of opinion sharing platform, namely question answering (QA) forum,
Both the issues of data deficiencies and semantic consistency are important for data augmentation. Most of previous methods address the first issue, but ignore the second one. In the cases of aspect-based sentiment analysis, violation of the above is