Comparative analysis of deep Siamese models for medical reports text similarity

Abstrak

Even though medical reports have been digitized, they are generally text data and have not been used optimally. Extracting information from these reports is challenging due to their high volume and unstructured nature. Analyzing the extraction of relevant and high-quality information can be achieved by measuring semantic textual similarity (STS). Consequently, the primary aim of this study is to develop and evaluate the performance of four models: Siamese Manhattan convolution neural network (CNN), Siamese Manhattan long short-term memory (LSTM), Siamese Manhattan hybrid CNN-LSTM, and Siamese Manhattan hybrid LSTM-CNN, in determining STS between sentence pairs in medical reports. Performance comparisons were conducted using Cosine Similarity and word mover's distance (WMD) methods. The results indicate that the Siamese Manhattan hybrid LSTM-CNN model outperforms the other models, with a similarity score of 1 for each sentence pair, signifying identical semantic meaning.