They Are Not the Same: Direct Causes Are Not Grounded Emotion Explanations
For researchers in emotion-cause extraction, the paper identifies a critical gap between the proxy task of direct-cause extraction and the goal of grounded emotion explanation, highlighting that high binary ECPE performance does not imply explanatory capability.
The paper shows that binary Emotion-Cause Pair Extraction (ECPE) tasks, while largely preserved (90.9% original positives remain emo-cause, 95.0% negatives remain non-pair), do not provide grounded emotion explanations because they miss emo-context and are vulnerable to shortcut learning, where models favor lexically similar non-pairs over structurally harder evidence-supported pairs.
Emotion-Cause Pair Extraction (ECPE) was introduced to explain why an emotion occurs, but this goal is now often reduced to binary pair/non-pair prediction. This proxy is useful for direct-cause extraction, yet easy to over-read as evidence grounded emotion explanation. We show that this interpretation is only partially valid. In IEMO-MECP, 90.9% of original positives remain emo-cause and 95.0% of original negatives remain non-pair, confirming that the binary ECPE task is largely preserved. The problem is that direct triggers alone do not constitute a grounded explanation. Emo-context, an utterance that helps interpret a target emotion without directly causing it, appears on both sides of the original boundary and is enriched near binary uncertainty, showing that the binary boundary has no stable place for such discourse evidence. Across evaluated ECPE models, direct triggers are recovered more reliably than contextual support. Under shortcut pressure, this imbalance becomes consequential. Binary-trained models assign higher pair scores to nearby lexically similar non-pair candidates than to evidence supported but structurally harder emo-cause and emo-context pairs. Thus, pair scores can reward convenient attributions over grounded explanations. High binary ECPE performance indicates that a model can identify direct triggers; it does not indicate that the model has explained the emotion. Code is publicly available at https://github.com/panzhzh/ECPExsame.