# Rethinking the Event Coding Pipeline with Prompt Entailment

arXiv: https://arxiv.org/abs/2210.05257 · HTML: https://mlsanity.com/paper/2210.05257/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 44 references that are in the map.
- First posted on arXiv 11 Oct 2022.

## Builds on (most cited first, 16 of 16)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference](https://mlsanity.com/paper/2001.07676/) (2020)
- [Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approach](https://mlsanity.com/paper/1909.00161/) (2019)
- [Constrained Language Models Yield Few-Shot Semantic Parsers](https://mlsanity.com/paper/2104.08768/) (2021)
- [Entailment as Few-Shot Learner](https://mlsanity.com/paper/2104.14690/) (2021)
- [Automatically Identifying Words That Can Serve as Labels for Few-Shot Text Classification](https://mlsanity.com/paper/2010.13641/) (2020)
- [Label Verbalization and Entailment for Effective Zero- and Few-Shot Relation Extraction](https://mlsanity.com/paper/2109.03659/) (2021)
- [Corpus-Level Evaluation for Event QA: The IndiaPoliceEvents Corpus Covering the 2002 Gujarat Violence](https://mlsanity.com/paper/2105.12936/) (2021)
- [An Ordinal Latent Variable Model of Conflict Intensity](https://mlsanity.com/paper/2210.03971/) (2022)
- [Classifying Dyads for Militarized Conflict Analysis](https://mlsanity.com/paper/2109.12860/) (2021)
- [SeismographAPI: Visualising Temporal-Spatial Crisis Data](https://mlsanity.com/paper/2107.12443/) (2021)

## Built on by (most cited first, 5 of 5)

- [Taxonomy-Aware Evaluation of Vision-Language Models](https://mlsanity.com/paper/2504.05457/) (2025)
- [Political DEBATE: Efficient Zero-shot and Few-shot Classifiers for Political Text](https://mlsanity.com/paper/2409.02078/) (2024)
- [ACTI at EVALITA 2023: Overview of the Conspiracy Theory Identification Task](https://mlsanity.com/paper/2307.06954/) (2023)
- [ConfliBERT: A Language Model for Political Conflict](https://mlsanity.com/paper/2412.15060/) (2024)
- [Extracting Victim Counts from Text](https://mlsanity.com/paper/2302.12367/) (2023)

## Abstract (arXiv)

For monitoring crises, political events are extracted from the news. The large amount of unstructured full-text event descriptions makes a case-by-case analysis unmanageable, particularly for low-resource humanitarian aid organizations. This creates a demand to classify events into event types, a task referred to as event coding. Typically, domain experts craft an event type ontology, annotators label a large dataset and technical experts develop a supervised coding system. In this work, we propose PR-ENT, a new event coding approach that is more flexible and resource-efficient, while maintaining competitive accuracy: first, we extend an event description such as "Military injured two civilians'' by a template, e.g. "People were [Z]" and prompt a pre-trained (cloze) language model to fill the slot Z. Second, we select answer candidates Z* = {"injured'', "hurt"...} by treating the event description as premise and the filled templates as hypothesis in a textual entailment task. This allows domain experts to draft the codebook directly as labeled prompts and interpretable answer candidates. This human-in-the-loop process is guided by our interactive codebook design tool. We evaluate PR-ENT in several robustness checks: perturbing the event description and prompt template, restricting the vocabulary and removing contextual information.