GSSF: A Generative Sequence Similarity Function based on a Seq2Seq model for clustering online handwritten mathematical answers

TL;DR

This paper introduces GSSF, a generative sequence similarity function based on a Seq2Seq model, to improve clustering of online handwritten mathematical expressions for assisting in computer-aided marking.

Contribution

It proposes a novel similarity measure using a Seq2Seq recognizer and demonstrates its effectiveness in clustering handwritten math answers.

Findings

Achieved high clustering purity (~0.916) on mixed datasets.

Reduced marking cost effectively compared to previous methods.

Outperformed existing clustering approaches for online handwritten math expressions.

Abstract

Toward a computer-assisted marking for descriptive math questions,this paper presents clustering of online handwritten mathematical expressions (OnHMEs) to help human markers to mark them efficiently and reliably. We propose a generative sequence similarity function for computing a similarity score of two OnHMEs based on a sequence-to-sequence OnHME recognizer. Each OnHME is represented by a similarity-based representation (SbR) vector. The SbR matrix is inputted to the k-means algorithm for clustering OnHMEs. Experiments are conducted on an answer dataset (Dset_Mix) of 200 OnHMEs mixed of real patterns and synthesized patterns for each of 10 questions and a real online handwritten mathematical answer dataset of 122 student answers at most for each of 15 questions (NIER_CBT). The best clustering results achieved around 0.916 and 0.915 for purity, and around 0.556 and 0.702 for the marking cost on Dset_Mix and NIER_CBT, respectively. Our method currently outperforms the previous methods for clustering HMEs.