# Event Knowledge Incorporation with Posterior Regularization for Event-Centric Question Answering

arXiv: https://arxiv.org/abs/2305.04522 · HTML: https://mlsanity.com/paper/2305.04522/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 21 of its 36 references that are in the map.
- First posted on arXiv 8 May 2023.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 21 of 21)

- [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)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [SpanBERT: Improving Pre-training by Representing and Predicting Spans](https://mlsanity.com/paper/1907.10529/) (2019)
- [Neural Text Generation with Unlikelihood Training](https://mlsanity.com/paper/1908.04319/) (2019)
- [UnifiedQA: Crossing Format Boundaries With a Single QA System](https://mlsanity.com/paper/2005.00700/) (2020)
- [Event Extraction by Answering (Almost) Natural Questions](https://mlsanity.com/paper/2004.13625/) (2020)
- ["Going on a vacation" takes longer than "Going for a walk": A Study of Temporal Commonsense Understanding](https://mlsanity.com/paper/1909.03065/) (2019)
- [Don't Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training](https://mlsanity.com/paper/1911.03860/) (2019)
- [ASER: A Large-scale Eventuality Knowledge Graph](https://mlsanity.com/paper/1905.00270/) (2019)
- [TORQUE: A Reading Comprehension Dataset of Temporal Ordering Questions](https://mlsanity.com/paper/2005.00242/) (2020)
- [Paragraph-level Simplification of Medical Texts](https://mlsanity.com/paper/2104.05767/) (2021)
- [ForecastQA: A Question Answering Challenge for Event Forecasting with Temporal Text Data](https://mlsanity.com/paper/2005.00792/) (2020)
- [ESTER: A Machine Reading Comprehension Dataset for Event Semantic Relation Reasoning](https://mlsanity.com/paper/2104.08350/) (2021)
- [Event-QA: A Dataset for Event-Centric Question Answering over Knowledge Graphs](https://mlsanity.com/paper/2004.11861/) (2020)
- [EventKG - the Hub of Event Knowledge on the Web - and Biographical Timeline Generation](https://mlsanity.com/paper/1905.08794/) (2019)
- [Prior Knowledge Integration for Neural Machine Translation using Posterior Regularization](https://mlsanity.com/paper/1811.01100/) (2018)
- [Robust Reading Comprehension with Linguistic Constraints via Posterior Regularization](https://mlsanity.com/paper/1911.06948/) (2019)
- [Event-Centric Question Answering via Contrastive Learning and Invertible Event Transformation](https://mlsanity.com/paper/2210.12902/) (2022)

## Built on by (most cited first, 1 of 1)

- [AlignSAE: Concept-Aligned Sparse Autoencoders](https://mlsanity.com/paper/2512.02004/) (2025)

## Abstract (arXiv)

We propose a simple yet effective strategy to incorporate event knowledge extracted from event trigger annotations via posterior regularization to improve the event reasoning capability of mainstream question-answering (QA) models for event-centric QA. In particular, we define event-related knowledge constraints based on the event trigger annotations in the QA datasets, and subsequently use them to regularize the posterior answer output probabilities from the backbone pre-trained language models used in the QA setting. We explore two different posterior regularization strategies for extractive and generative QA separately. For extractive QA, the sentence-level event knowledge constraint is defined by assessing if a sentence contains an answer event or not, which is later used to modify the answer span extraction probability. For generative QA, the token-level event knowledge constraint is defined by comparing the generated token from the backbone language model with the answer event in order to introduce a reward or penalty term, which essentially adjusts the answer generative probability indirectly. We conduct experiments on two event-centric QA datasets, TORQUE and ESTER. The results show that our proposed approach can effectively inject event knowledge into existing pre-trained language models and achieves strong performance compared to existing QA models in answer evaluation. Code and models can be found: https://github.com/LuJunru/EventQAviaPR.