This paper introduces DiscoFlan, a multilingual discourse relation classifier submitted for DISRPT 2023. Our submission represents the first attempt at building a multilingual discourse relation classifier for the DISRPT 2023 shared task. By our model addresses the issue to mismatches caused by hallucination in a seq2seq model by utilizing the label distribution information for label generation. In contrast to the previous state-of-the-art model, our approach eliminates the need for hand-crafted features in computing the discourse relation classes. Furthermore, we propose a novel label generation mechanism that anchors the labels to a fixed set by selectively enhancing training on the decoder model. Our experimental results demonstrate that our model surpasses the current state-of-the-art performance in 11 out of the 26 datasets considered, however the submitted model compatible with provided evaluation scripts is better in 7 out of 26 considered datasets, while demonstrating competitive results in the rest. Overall, DiscoFlan showcases promising advancements in multilingual discourse relation classification for the DISRPT 2023 shared task.

In discourse relation recognition, the classification labels are typically represented as one-hot vectors. However, the categories are in fact not all independent of one another on the contrary, there are several frameworks that describe the labels’ similarities (by e.g. sorting them into a hierarchy or describing them interms of features (Sanders et al., 2021)). Recently, several methods for representing the similarities between labels have been proposed (Zhang et al., 2018; Wang et al., 2018; Xiong et al., 2021). We here explore and extend the Label Confusion Model (Guo et al., 2021) for learning a representation for discourse relation labels. We explore alternative ways of informing the model about the similarities between relations, by representing relations in terms of their names (and parent category), their typical markers, or in terms of CCR features that describe the relations. Experimental results show that exploiting label similarity improves classification results.

Implicit discourse relations can convey more than one relation sense, but much of the research on discourse relations has focused on single relation senses. Recently, DiscoGeM, a novel multi-domain corpus, which contains 10 crowd-sourced labels per relational instance, has become available. In this paper, we analyse the co-occurrences of relations in DiscoGem and show that they are systematic and characteristic of text genre. We then test whether information on multi-label distributions in the data can help implicit relation classifiers. Our results show that incorporating multiple labels in parser training can improve its performance, and yield label distributions which are more similar to human label distributions, compared to a parser that is trained on just a single most frequent label per instance.

While Curriculum Learning (CL) has recently gained traction in Natural language Processing Tasks, it is still not adequately analyzed. Previous works only show their effectiveness but fail short to explain and interpret the internal workings fully. In this paper, we analyze curriculum learning in sentiment analysis along multiple axes. Some of these axes have been proposed by earlier works that need more in-depth study. Such analysis requires understanding where curriculum learning works and where it does not. Our axes of analysis include Task difficulty on CL, comparing CL pacing techniques, and qualitative analysis by visualizing the movement of attention scores in the model as curriculum phases progress. We find that curriculum learning works best for difficult tasks and may even lead to a decrement in performance for tasks with higher performance without curriculum learning. We see that One-Pass curriculum strategies suffer from catastrophic forgetting and attention movement visualization within curriculum pacing. This shows that curriculum learning breaks down the challenging main task into easier sub-tasks solved sequentially.