FILM: A Fast, Interpretable, and Low-rank Metric Learning Approach for Sentence Matching

TL;DR

The paper introduces FILM, a fast, interpretable, low-rank metric learning method for sentence matching that achieves high accuracy and speed, addressing interpretability and efficiency issues in current models.

Contribution

It proposes a novel metric learning approach using manifold optimization and Cayley transformation, enhancing interpretability and computational efficiency in sentence similarity tasks.

Findings

FILM outperforms existing methods in accuracy.

FILM achieves the fastest computation speed.

Theoretical analysis confirms its efficiency.

Abstract

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.