{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/rethinking-the-event-coding-pipeline-with","title":"Rethinking the Event Coding Pipeline with Prompt Entailment","arxiv_id":"2210.05257","date":"2022-10-11","proceeding":null,"authors":["Clément Lefebvre","Niklas Stoehr"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2210.05257v2","url_pdf":"https://arxiv.org/pdf/2210.05257v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"rethinking-the-event-coding-pipeline-with","repo_url":"https://github.com/clement-lef/pr-ent","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"humanitarian","task_name":"Humanitarian"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.05257","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}