# Learning Soft Linear Constraints with Application to Citation Field Extraction

arXiv: https://arxiv.org/abs/1403.1349 · HTML: https://mlsanity.com/paper/1403.1349/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Mar 2014.

## Built on by (most cited first, 8 of 8)

- [Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey](https://mlsanity.com/paper/2411.17558/) (2024)
- [Dual-path Collaborative Generation Network for Emotional Video Captioning](https://mlsanity.com/paper/2408.03006/) (2024)
- [GS-Cache: A GS-Cache Inference Framework for Large-scale Gaussian Splatting Models](https://mlsanity.com/paper/2502.14938/) (2025)
- [RetouchingFFHQ: A Large-scale Dataset for Fine-grained Face Retouching Detection](https://mlsanity.com/paper/2307.10642/) (2023)
- [MARL-MambaContour: Unleashing Multi-Agent Deep Reinforcement Learning for Active Contour Optimization in Medical Image Segmentation](https://mlsanity.com/paper/2506.18679/) (2025)
- [Source or It Didn't Happen: A Multi-Agent Framework for Citation Hallucination Detection](https://mlsanity.com/paper/2605.08583/) (2026)
- [Linguistically-Informed Neural Architectures for Lexical, Syntactic and Semantic Tasks in Sanskrit](https://mlsanity.com/paper/2308.08807/) (2023)
- [Making Sense of Data in the Wild: Data Analysis Automation at Scale](https://mlsanity.com/paper/2502.15718/) (2025)

## Abstract (arXiv)

Accurately segmenting a citation string into fields for authors, titles, etc. is a challenging task because the output typically obeys various global constraints. Previous work has shown that modeling soft constraints, where the model is encouraged, but not require to obey the constraints, can substantially improve segmentation performance. On the other hand, for imposing hard constraints, dual decomposition is a popular technique for efficient prediction given existing algorithms for unconstrained inference. We extend the technique to perform prediction subject to soft constraints. Moreover, with a technique for performing inference given soft constraints, it is easy to automatically generate large families of constraints and learn their costs with a simple convex optimization problem during training. This allows us to obtain substantial gains in accuracy on a new, challenging citation extraction dataset.