Measuring Semantic Similarity Between Sentences Using A Siamese Neural Network
Alexandre Yukio Ichida, Felipe Rech Meneguzzi, Duncan D. Ruiz · 2018
The task of measure semantic redundancy between sentences demands a thorough interpretation from the reader because phrase meaning may be ambiguous. Detecting semantic similarity is a difficult problem because natural language, besides ambiguity, offers almost infinite possibilities to express the same idea. This paper adapts a siamese neural network architecture trained to measure the semantic similarity between two sentences through metric learning. The resulting solution should help in writing more efficient and informative text.