@inproceedings{liakhovets-schlarb-2022-zero,
    title = "Zero-shot Event Causality Identification with Question Answering",
    author = "Liakhovets, Daria  and
      Schlarb, Sven",
    booktitle = "Proceedings of the Fifth International Conference on Computational Linguistics in Bulgaria (CLIB 2022)",
    month = sep,
    year = "2022",
    address = "Sofia, Bulgaria",
    publisher = "Department of Computational Linguistics, IBL -- BAS",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2022.clib-1.13/",
    pages = "113--119",
    abstract = "Extraction of event causality and especially implicit causality from text data is a challenging task. Causality is often treated as a specific relation type and can be considered as a part of relation extraction or relation classification task. Many causality identification-related tasks are designed to select the most plausible alternative of a set of possible causes and consider multiple-choice classification settings. Since there are powerful Question Answering (QA) systems pretrained on large text corpora, we investigated a zero-shot QA-based approach for event causality extraction using a Wikipedia-based dataset containing event descriptions (articles) and annotated causes. We aimed to evaluate to what extent reading comprehension ability of the QA-pipeline can be used for event-related causality extraction from plain text without any additional training. Some evaluation challenges and limitations of the data were discussed. We compared the performance of a two-step pipeline consisting of passage retrieval and extractive QA with QA-only pipeline on event-associated articles and mixed ones. Our systems achieved average cosine semantic similarity scores of 44 {--} 45{\%} in different settings."
}