Weakly Supervised Concept Map Generation through Task-Guided Graph Translation

TL;DR

This paper introduces GT-D2G, a weakly supervised framework that generates task-oriented concept maps from texts by translating initial semantic graphs, improving interpretability and classification performance.

Contribution

The work presents a novel graph translation approach for concept map generation that requires minimal supervision and enhances downstream task performance.

Findings

GT-D2G outperforms existing methods in concept map quality.

Human evaluation confirms the interpretability of generated maps.

GT-D2G demonstrates label efficiency and flexible graph sizing.

Abstract

Recent years have witnessed the rapid development of concept map generation techniques due to their advantages in providing well-structured summarization of knowledge from free texts. Traditional unsupervised methods do not generate task-oriented concept maps, whereas deep generative models require large amounts of training data. In this work, we present GT-D2G (Graph Translation-based Document To Graph), an automatic concept map generation framework that leverages generalized NLP pipelines to derive semantic-rich initial graphs, and translates them into more concise structures under the weak supervision of downstream task labels. The concept maps generated by GT-D2G can provide interpretable summarization of structured knowledge for the input texts, which are demonstrated through human evaluation and case studies on three real-world corpora. Further experiments on the downstream task of document classification show that GT-D2G beats other concept map generation methods. Moreover, we specifically validate the labeling efficiency of GT-D2G in the label-efficient learning setting and the flexibility of generated graph sizes in controlled hyper-parameter studies.