CONF Burdisso_CASE@EMNLP2022_2022/IDIAP IDIAPers @ Causal News Corpus 2022: Efficient Causal Relation Identification Through a Prompt-based Few-shot Approach Burdisso, Sergio Zuluaga-Gomez, Juan Villatoro-Tello, Esaú Fajcik, Martin Singh, Muskaan Smrz, Pavel Motlicek, Petr https://publications.idiap.ch/index.php/publications/showcite/Burdisso_Idiap-RR-13-2022 Related documents The 5th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE @ EMNLP 2022) 2022 ACL Anthology (https://aclanthology.org/2022.case-1.9) https://preview.aclanthology.org/emnlp-22-ingestion/2022.case-1.9/ URL In this paper, we describe our participation in the subtask 1 of CASE-2022, Event Causality Identification with Casual News Corpus. We address the Causal Relation Identification (CRI) task by exploiting a set of simple yet complementary techniques for fine-tuning language models (LMs) on a small number of annotated examples (i.e., a few-shot configuration). We follow a prompt-based prediction approach for fine-tuning LMs in which the CRI task is treated as a masked language modeling problem (MLM). This approach allows LMs natively pre-trained on MLM problems to directly generate textual responses to CRI-specific prompts. We compare the performance of this method against ensemble techniques trained on the entire dataset. Our best-performing submission was fine-tuned with only 256 instances per class, 15.7% of the all available data, and yet obtained the second-best precision (0.82), third-best accuracy (0.82), and an F1-score (0.85) very close to what was reported by the winner team (0.86). REPORT Burdisso_Idiap-RR-13-2022/IDIAP IDIAPers @ Causal News Corpus 2022: Efficient Causal Relation Identification Through a Prompt-based Few-shot Approach Burdisso, Sergio Zuluaga-Gomez, Juan Villatoro-Tello, Esaú Fajcik, Martin Singh, Muskaan Smrz, Pavel Motlicek, Petr EXTERNAL https://publications.idiap.ch/attachments/reports/2022/Burdisso_Idiap-RR-13-2022.pdf PUBLIC Idiap-RR-13-2022 2022 Idiap November 2022 In this paper, we describe our participation in the subtask 1 of CASE-2022, Event Causality Identification with Casual News Corpus. We address the Causal Relation Identification (CRI) task by exploiting a set of simple yet complementary techniques for fine-tuning language models (LMs) on a small number of annotated examples (i.e., a few-shot configuration). We follow a prompt-based prediction approach for fine-tuning LMs in which the CRI task is treated as a masked language modeling problem (MLM). This approach allows LMs natively pre-trained on MLM problems to directly generate textual responses to CRI-specific prompts. We compare the performance of this method against ensemble techniques trained on the entire dataset. Our best-performing submission was trained only with 256 instances per class, a small portion of the entire dataset, and yet was able to obtain the second best precision (0.82), third best accuracy (0.82), and an F1-score ($0.85$) very close to what was reported by the winner team (0.86).