The paper introduces a novel neural network model called Attention-Based Bidirectional Long Short-Term Memory Networks (Att-BLSTM) for relation classification in natural language processing (NLP). The model aims to capture the most important semantic information in a sentence without relying on lexical resources or NLP systems like dependency parsers and named entity recognizers (NER). The Att-BLSTM model consists of an input layer, embedding layer, LSTM layer, attention layer, and output layer. The attention mechanism allows the model to focus on the most relevant words, enhancing the classification performance. Experimental results on the SemEval-2010 relation classification task show that the Att-BLSTM model outperforms most existing methods, achieving an F1-score of 84.0%. The model's effectiveness is demonstrated through its ability to automatically learn high-level features from raw text, making it a simpler and more efficient alternative to traditional methods.The paper introduces a novel neural network model called Attention-Based Bidirectional Long Short-Term Memory Networks (Att-BLSTM) for relation classification in natural language processing (NLP). The model aims to capture the most important semantic information in a sentence without relying on lexical resources or NLP systems like dependency parsers and named entity recognizers (NER). The Att-BLSTM model consists of an input layer, embedding layer, LSTM layer, attention layer, and output layer. The attention mechanism allows the model to focus on the most relevant words, enhancing the classification performance. Experimental results on the SemEval-2010 relation classification task show that the Att-BLSTM model outperforms most existing methods, achieving an F1-score of 84.0%. The model's effectiveness is demonstrated through its ability to automatically learn high-level features from raw text, making it a simpler and more efficient alternative to traditional methods.