# What Causes the Failure of Explicit to Implicit Discourse Relation Recognition?

arXiv: https://arxiv.org/abs/2404.00999 · HTML: https://mlsanity.com/paper/2404.00999/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 50 references that are in the map.
- First posted on arXiv 1 Apr 2024.

## Builds on (most cited first, 10 of 10)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Facilitating Contrastive Learning of Discourse Relational Senses by Exploiting the Hierarchy of Sense Relations](https://mlsanity.com/paper/2301.02724/) (2023)
- [Adversarial Connective-exploiting Networks for Implicit Discourse Relation Classification](https://mlsanity.com/paper/1704.00217/) (2017)
- [Prompt-based Connective Prediction Method for Fine-grained Implicit Discourse Relation Recognition](https://mlsanity.com/paper/2210.07032/) (2022)
- [Annotation-Inspired Implicit Discourse Relation Classification with Auxiliary Discourse Connective Generation](https://mlsanity.com/paper/2306.06480/) (2023)
- [Let's be explicit about that: Distant supervision for implicit discourse relation classification via connective prediction](https://mlsanity.com/paper/2106.03192/) (2021)
- [Zero-shot transfer for implicit discourse relation classification](https://mlsanity.com/paper/1907.12885/) (2019)
- [Unsupervised Adversarial Domain Adaptation for Implicit Discourse Relation Classification](https://mlsanity.com/paper/2003.02244/) (2020)
- [TEPrompt: Task Enlightenment Prompt Learning for Implicit Discourse Relation Recognition](https://mlsanity.com/paper/2305.10866/) (2023)
- [What's Hard in English RST Parsing? Predictive Models for Error Analysis](https://mlsanity.com/paper/2309.04940/) (2023)

## Built on by (most cited first, 4 of 4)

- [A Multi-Level Benchmark for Causal Language Understanding in Social Media Discourse](https://mlsanity.com/paper/2509.16722/) (2025)
- [Joint Modeling of Entities and Discourse Relations for Coherence Assessment](https://mlsanity.com/paper/2509.04182/) (2025)
- [Synthetic Data Augmentation for Cross-domain Implicit Discourse Relation Recognition](https://mlsanity.com/paper/2503.20588/) (2025)
- [Beyond Supervised Clarification: Input Rewriting with LLMs for Dialogue Discourse Parsing](https://mlsanity.com/paper/2607.01964/) (2026)

## Abstract (arXiv)

We consider an unanswered question in the discourse processing community: why do relation classifiers trained on explicit examples (with connectives removed) perform poorly in real implicit scenarios? Prior work claimed this is due to linguistic dissimilarity between explicit and implicit examples but provided no empirical evidence. In this study, we show that one cause for such failure is a label shift after connectives are eliminated. Specifically, we find that the discourse relations expressed by some explicit instances will change when connectives disappear. Unlike previous work manually analyzing a few examples, we present empirical evidence at the corpus level to prove the existence of such shift. Then, we analyze why label shift occurs by considering factors such as the syntactic role played by connectives, ambiguity of connectives, and more. Finally, we investigate two strategies to mitigate the label shift: filtering out noisy data and joint learning with connectives. Experiments on PDTB 2.0, PDTB 3.0, and the GUM dataset demonstrate that classifiers trained with our strategies outperform strong baselines.