Constrained Sequence-to-Tree Generation for Hierarchical Text Classification
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.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATIONtext-classificationText ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
A Hierarchical Language Model with Predictable Scaling Laws and Provable Benefits of Reasoning
We introduce a family of synthetic languages with hierarchical structure -- generated by a broadcast process on trees -- for which the role of context length and reasoning in autoregressive generation can be analyzed pre…
From Pixels to Hierarchical Sequences: Quadtree Mask Encoding for Vision-Language Binary Change Detection
Dense change detection in remote sensing requires vision-language models (VLMs) to compare bi-temporal images and generate accurate pixel-level masks. Existing VLMs are largely confined to change captioning outputs, and …
Change DetectionOctree Transformer: Autoregressive 3D Shape Generation on Hierarchically Structured Sequences
Autoregressive models have proven to be very powerful in NLP text generation tasks and lately have gained popularity for image generation as well. However, they have seen limited use for the synthesis of 3D shapes so far…
3D Shape GenerationImage GenerationText GenerationTree Decomposition Attention for AMR-to-Text Generation
Text generation from AMR requires mapping a semantic graph to a string that it annotates. Transformer-based graph encoders, however, poorly capture vertex dependencies that may benefit sequence prediction. To impose orde…
AMR-to-Text GenerationText GenerationTop-Down Structurally-Constrained Neural Response Generation with Lexicalized Probabilistic Context-Free Grammar
We consider neural language generation under a novel problem setting: generating the words of a sentence according to the order of their first appearance in its lexicalized PCFG parse tree, in a depth-first, left-to-righ…
DiversityResponse GenerationSentenceText Generation