LTRC @ Causal News Corpus 2022: Extracting and Identifying Causal Elements using Adapters

Hiranmai Sri Adibhatla, Manish Shrivastava

Abstract

Identifying causal relationships in natural language is a fundamental challenge in NLP. This paper describes the system developed by team LTRC for the CASE 2022 shared task on the Causal News Corpus. We employ parameter-efficient adapters integrated into pre-trained Transformer models to perform causal event classification and span detection. Our approach demonstrates that freezing model weights and training small bottleneck layers can yield competitive results, ranking 3rd in causal classification and 4th in span extraction.

Introduction

Event Causality Identification (ECI) involves detecting whether a sentence describes a cause-and-effect relationship and identifying the specific text spans representing the cause, the effect, and the linguistic signal connecting them. This task is critical for applications ranging from financial analysis to socio-political event monitoring. However, full fine-tuning of large language models for such niche tasks is often computationally prohibitive and prone to overfitting.

Examples of causal and non-causal sentences with annotated spans for cause (green), effect (purple), and signal (blue).

Methodology

We utilized a Transformer-based architecture enhanced with Adapters. Adapters are small, trainable bottleneck layers inserted between the existing layers of a frozen pre-trained model. This allows for task-specific tuning without modifying the original model weights, preserving general linguistic knowledge.

Subtask 1: Causal Event Classification

For determining if a sentence contains a causal relation, we experimented with BART-large, RoBERTa-large, and RoBERTa-base. We found that RoBERTa-base with an adapter and a simple classification head provided the best balance of performance and efficiency.

Subtask 2: Cause-Effect-Signal Span Detection

This subtask was framed as a sequence labeling problem using IOB (Inside-Outside-Beginning) tagging. We employed BERT-base with adapters to label each token. To ensure valid sequence predictions, we implemented four heuristic post-processing rules to clean the predicted spans.

Data

The primary dataset was the Causal News Corpus (CNC), containing 3,559 event sentences from news articles. To improve model robustness, we augmented the training data with UniCausal, a larger unified benchmark for causal text mining, resulting in a combined training set of 6,767 samples.

Results and Discussion

Our system achieved a binary F1 score of 0.853 in Subtask 1, placing 3rd in the competition. In Subtask 2, we reached a macro F1 score of 0.032, ranking 4th.

Performance comparison of different model architectures on the classification subtask. RoBERTa-base with an adapter achieved the highest F1 score.

The relatively low scores in span detection highlight the extreme difficulty of identifying "signals"—short, common words like "because" or "led to"—which models often overlook. Error analysis further revealed that linguistic ambiguities, such as polysemous words (e.g., "fast" as a noun vs. adjective) and idioms (e.g., "raining bombs"), remain significant hurdles for current Transformer architectures.

Conclusion

This work demonstrates the effectiveness of parameter-efficient adapters for specialized NLP tasks like causality extraction. Future improvements could involve ensemble modeling, the addition of CRF layers to better capture sequence dependencies, and the incorporation of syntactic features like POS tags to disambiguate complex sentence structures.

Summary updated

Abstract

Causality detection and identification is centered on identifying semantic and cognitive connections in a sentence. In this paper, we describe the effort of team LTRC for Causal News Corpus - Event Causality Shared Task 2022 at the 5th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE 2022). The shared task consisted of two subtasks: 1) identifying if a sentence contains a causality relation, and 2) identifying spans of text that correspond to cause, effect and signals. We fine-tuned transformer-based models with adapters for both subtasks. Our best-performing models obtained a binary F1 score of 0.853 on held-out data for subtask 1 and a macro F1 score of 0.032 on held-out data for subtask 2. Our approach is ranked third in subtask 1 and fourth in subtask 2. The paper describes our experiments, solutions, and analysis in detail.
BibTeX
@inproceedings{adibhatla2022ltrc,
  author = {Hiranmai Sri Adibhatla and Manish Shrivastava},
  title = {{LTRC @ Causal News Corpus 2022: Extracting and Identifying Causal Elements using Adapters}},
  booktitle = {CASE @ EMNLP},
  year = {2022},
  doi = {10.18653/v1/2022.case-1.7},
}
Figure