Constrained Sequence-to-Tree Generation for Hierarchical Text Classification

TL;DR

This paper introduces Seq2Tree, a sequence-to-tree framework with constrained decoding for hierarchical text classification, improving label consistency and performance over previous flat classification methods.

Contribution

The paper proposes a novel sequence-to-tree approach with dynamic vocabulary decoding to better model hierarchical labels in text classification.

Findings

Significant improvements on three benchmark datasets.

Enhanced label consistency in hierarchical classification.

Outperforms previous flat classification approaches.

Abstract

Hierarchical Text Classification (HTC) is a challenging task where a document can be assigned to multiple hierarchically structured categories within a taxonomy. The majority of prior studies consider HTC as a flat multi-label classification problem, which inevitably leads to "label inconsistency" problem. In this paper, we formulate HTC as a sequence generation task and introduce a sequence-to-tree framework (Seq2Tree) for modeling the hierarchical label structure. Moreover, we design a constrained decoding strategy with dynamic vocabulary to secure the label consistency of the results. Compared with previous works, the proposed approach achieves significant and consistent improvements on three benchmark datasets.