FILM: A Fast, Interpretable, and Low-rank Metric Learning Approach for Sentence Matching
This work addresses the need for efficient and interpretable sentence matching in natural language processing, offering a novel method that improves speed and performance over existing approaches.
The paper tackled the problem of semantic similarity detection in sentence matching by proposing FILM, a fast, interpretable, and low-rank metric learning approach, which achieved superior performance and the fastest computation speed on the Quora Challenge and STS Task.
Detection of semantic similarity plays a vital role in sentence matching. It requires to learn discriminative representations of natural language. Recently, owing to more and more sophisticated model architecture, impressive progress has been made, along with a time-consuming training process and not-interpretable inference. To alleviate this problem, we explore a metric learning approach, named FILM (Fast, Interpretable, and Low-rank Metric learning) to efficiently find a high discriminative projection of the high-dimensional data. We construct this metric learning problem as a manifold optimization problem and solve it with the Cayley transformation method with the Barzilai-Borwein step size. In experiments, we apply FILM with triplet loss minimization objective to the Quora Challenge and Semantic Textual Similarity (STS) Task. The results demonstrate that the FILM method achieves superior performance as well as the fastest computation speed, which is consistent with our theoretical analysis of time complexity.