The Novel Sequence Distance Measuring Algorithm Based on Optimal Transport and Cross‐Attention Mechanism

Abstract

In this paper, we propose a novel sequence distance measuring algorithm based on optimal transport (OT) and cross-attention mechanism. Given a source sequence and a target sequence, we first calculate the ground distance between each pair of source and target terms of the two sequences. The ground distance is calculated over the subsequences around the two terms. We firstly pay attention from each the source terms to each target terms with attention weights, so that we have a representative source subsequence vector regarding each term in the target subsequence. Then, we pay attention from each representative vector of the term of the target subsequence to the entire source subsequence. In this way, we construct the cross-attention weights and use them to calculate the pairwise ground distances. With the ground distances, we derive the OT distance between the two sequences and train the attention parameters and ground distance metric parameters together. The training process is conducted with training triplets of sequences, where each triplet is composed of an anchor sequence, a must-link sequence, and a cannot-link sequence. The corresponding hinge loss function of each triplet is minimized, and we develop an iterative algorithm to solve the optimal transport problem and the attention/ground distance metric parameters in an alternate way. The experiments over sequence similarity search benchmark datasets, including text, video, and rice smut protein sequence data, are conducted. The experimental results show the algorithm is effective.

English Speech Scoring System Based on Computer Neural Network

“…Speech feature recognition focuses on the training of speech signal features, and uses machine learning to recognize semantics and convert them into characters. After the speech is recognized as a text, it is compared with the original text information to calculate the similarity of the two paragraphs of text [10], and the results are presented by scores.…”