# Expert Knowledge-Guided Length-Variant Hierarchical Label Generation for Proposal Classification

arXiv: https://arxiv.org/abs/2109.06661 · HTML: https://mlsanity.com/paper/2109.06661/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 33 references that are in the map.
- First posted on arXiv 14 Sep 2021.

## Builds on (most cited first, 11 of 11)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Distributed Representations of Sentences and Documents](https://mlsanity.com/paper/1405.4053/) (2014)
- [Multi-Label Classification Neural Networks with Hard Logical Constraints](https://mlsanity.com/paper/2103.13427/) (2021)
- [Hyperbolic Interaction Model For Hierarchical Multi-Label Classification](https://mlsanity.com/paper/1905.10802/) (2019)
- [Hierarchical Metadata-Aware Document Categorization under Weak Supervision](https://mlsanity.com/paper/2010.13556/) (2020)
- [Learn Class Hierarchy using Convolutional Neural Networks](https://mlsanity.com/paper/2005.08622/) (2020)

## Built on by (most cited first, 9 of 9)

- [COMAE: COMprehensive Attribute Exploration for Zero-shot Hashing](https://mlsanity.com/paper/2402.16424/) (2024)
- [Resolving the Imbalance Issue in Hierarchical Disciplinary Topic Inference via LLM-based Data Augmentation](https://mlsanity.com/paper/2310.05318/) (2023)
- [Hierarchical Interdisciplinary Topic Detection Model for Research Proposal Classification](https://mlsanity.com/paper/2209.13519/) (2022)
- [Interdisciplinary Fairness in Imbalanced Research Proposal Topic Inference: A Hierarchical Transformer-based Method with Selective Interpolation](https://mlsanity.com/paper/2309.01717/) (2023)
- [NEEDED: Introducing Hierarchical Transformer to Eye Diseases Diagnosis](https://mlsanity.com/paper/2212.13408/) (2022)
- [Who Should Review Your Proposal? Interdisciplinary Topic Path Detection for Research Proposals](https://mlsanity.com/paper/2203.10922/) (2022)
- [Hierarchical MixUp Multi-label Classification with Imbalanced Interdisciplinary Research Proposals](https://mlsanity.com/paper/2209.13912/) (2022)
- [Knowledge-Driven Agentic Scientific Corpus Distillation Framework for Biomedical Large Language Models Training](https://mlsanity.com/paper/2504.19565/) (2025)
- [SciHorizon-GENE: Benchmarking LLM for Life Sciences Inference from Gene Knowledge to Functional Understanding](https://mlsanity.com/paper/2601.12805/) (2026)

## Abstract (arXiv)

To advance the development of science and technology, research proposals are submitted to open-court competitive programs developed by government agencies (e.g., NSF). Proposal classification is one of the most important tasks to achieve effective and fair review assignments. Proposal classification aims to classify a proposal into a length-variant sequence of labels. In this paper, we formulate the proposal classification problem into a hierarchical multi-label classification task. Although there are certain prior studies, proposal classification exhibit unique features: 1) the classification result of a proposal is in a hierarchical discipline structure with different levels of granularity; 2) proposals contain multiple types of documents; 3) domain experts can empirically provide partial labels that can be leveraged to improve task performances. In this paper, we focus on developing a new deep proposal classification framework to jointly model the three features. In particular, to sequentially generate labels, we leverage previously-generated labels to predict the label of next level; to integrate partial labels from experts, we use the embedding of these empirical partial labels to initialize the state of neural networks. Our model can automatically identify the best length of label sequence to stop next label prediction. Finally, we present extensive results to demonstrate that our method can jointly model partial labels, textual information, and semantic dependencies in label sequences, and, thus, achieve advanced performances.