Multi-Lingual Implicit Discourse Relation Recognition with Multi-Label Hierarchical Learning
This work addresses the challenge of multi-lingual and multi-label classification in discourse analysis, which is important for natural language processing applications, but it is incremental as it builds on existing hierarchical methods and pre-trained encoders.
This paper tackles the problem of implicit discourse relation recognition across multiple languages and labels by introducing HArch, a model that leverages hierarchical dependencies in discourse senses. The results show that fine-tuned models like RoBERTa-HArch and XLM-RoBERTa-HArch outperform large language models such as GPT-4o and Llama-4-Maverick in few-shot settings, achieving state-of-the-art performance on the DiscoGeM 1.0 corpus.
This paper introduces the first multi-lingual and multi-label classification model for implicit discourse relation recognition (IDRR). Our model, HArch, is evaluated on the recently released DiscoGeM 2.0 corpus and leverages hierarchical dependencies between discourse senses to predict probability distributions across all three sense levels in the PDTB 3.0 framework. We compare several pre-trained encoder backbones and find that RoBERTa-HArch achieves the best performance in English, while XLM-RoBERTa-HArch performs best in the multi-lingual setting. In addition, we compare our fine-tuned models against GPT-4o and Llama-4-Maverick using few-shot prompting across all language configurations. Our results show that our fine-tuned models consistently outperform these LLMs, highlighting the advantages of task-specific fine-tuning over prompting in IDRR. Finally, we report SOTA results on the DiscoGeM 1.0 corpus, further validating the effectiveness of our hierarchical approach.