# Learning Constraints and Descriptive Segmentation for Subevent Detection

arXiv: https://arxiv.org/abs/2109.06316 · HTML: https://mlsanity.com/paper/2109.06316/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 39 references that are in the map.
- First posted on arXiv 13 Sep 2021.

## Builds on (most cited first, 18 of 18)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [On the Convergence of Adam and Beyond](https://mlsanity.com/paper/1904.09237/) (2019)
- [End-to-End Differentiable Proving](https://mlsanity.com/paper/1705.11040/) (2017)
- [Task-Oriented Dialogue as Dataflow Synthesis](https://mlsanity.com/paper/2009.11423/) (2020)
- [Text Segmentation as a Supervised Learning Task](https://mlsanity.com/paper/1803.09337/) (2018)
- [A Logic-Driven Framework for Consistency of Neural Models](https://mlsanity.com/paper/1909.00126/) (2019)
- [SparseMAP: Differentiable Sparse Structured Inference](https://mlsanity.com/paper/1802.04223/) (2018)
- [Text Segmentation by Cross Segment Attention](https://mlsanity.com/paper/2004.14535/) (2020)
- [Joint Constrained Learning for Event-Event Relation Extraction](https://mlsanity.com/paper/2010.06727/) (2020)
- [Augmenting Neural Networks with First-order Logic](https://mlsanity.com/paper/1906.06298/) (2019)
- [Temporal Common Sense Acquisition with Minimal Supervision](https://mlsanity.com/paper/2005.04304/) (2020)
- [Analogous Process Structure Induction for Sub-event Sequence Prediction](https://mlsanity.com/paper/2010.08525/) (2020)
- [Incidental Supervision: Moving beyond Supervised Learning](https://mlsanity.com/paper/2005.12339/) (2020)
- [Structured Tuning for Semantic Role Labeling](https://mlsanity.com/paper/2005.00496/) (2020)
- [Expressiveness of Rectifier Networks](https://mlsanity.com/paper/1511.05678/) (2015)
- [Learning Constraints for Structured Prediction Using Rectifier Networks](https://mlsanity.com/paper/2006.01209/) (2020)
- [Neural Article Pair Modeling for Wikipedia Sub-article Matching](https://mlsanity.com/paper/1807.11689/) (2018)

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

- [MAVEN-ERE: A Unified Large-scale Dataset for Event Coreference, Temporal, Causal, and Subevent Relation Extraction](https://mlsanity.com/paper/2211.07342/) (2022)
- [Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoning](https://mlsanity.com/paper/2305.16646/) (2023)
- [Improving Large Language Models in Event Relation Logical Prediction](https://mlsanity.com/paper/2310.09158/) (2023)
- [SubeventWriter: Iterative Sub-event Sequence Generation with Coherence Controller](https://mlsanity.com/paper/2210.06694/) (2022)
- [Zero-Shot On-the-Fly Event Schema Induction](https://mlsanity.com/paper/2210.06254/) (2022)
- [Topical Segmentation of Spoken Narratives: A Test Case on Holocaust Survivor Testimonies](https://mlsanity.com/paper/2210.13783/) (2022)
- [Beyond Grounding: Extracting Fine-Grained Event Hierarchies Across Modalities](https://mlsanity.com/paper/2206.07207/) (2022)
- [On Regularization and Inference with Label Constraints](https://mlsanity.com/paper/2307.03886/) (2023)
- [Are All Steps Equally Important? Benchmarking Essentiality Detection of Events](https://mlsanity.com/paper/2210.04074/) (2022)

## Abstract (arXiv)

Event mentions in text correspond to real-world events of varying degrees of granularity. The task of subevent detection aims to resolve this granularity issue, recognizing the membership of multi-granular events in event complexes. Since knowing the span of descriptive contexts of event complexes helps infer the membership of events, we propose the task of event-based text segmentation (EventSeg) as an auxiliary task to improve the learning for subevent detection. To bridge the two tasks together, we propose an approach to learning and enforcing constraints that capture dependencies between subevent detection and EventSeg prediction, as well as guiding the model to make globally consistent inference. Specifically, we adopt Rectifier Networks for constraint learning and then convert the learned constraints to a regularization term in the loss function of the neural model. Experimental results show that the proposed method outperforms baseline methods by 2.3% and 2.5% on benchmark datasets for subevent detection, HiEve and IC, respectively, while achieving a decent performance on EventSeg prediction.