Lune

ACL Findings2024

Multi-Label Classification for Implicit Discourse Relation Recognition

Wanqiu Long, Siddharth Narayanaswamy, Bonnie Webber

Abstract

Discourse relations play a pivotal role in establishing coherence within textual content, uniting sentences and clauses into a cohesive narrative. The Penn Discourse Treebank (PDTB) stands as one of the most extensively utilized datasets in this domain. In PDTB-3 (Webber et al., 2019), the annotators can assign multiple labels to an example, when they believe that multiple relations are present. Prior research in discourse relation recognition has treated these instances as separate examples during training, and only one example needs to have its label predicted correctly for the instance to be judged as correct. However, this approach is inadequate, as it fails to account for the interdependence of labels in real-world contexts and to distinguish between cases where only one sense relation holds and cases where multiple relations hold simultaneously. In our work, we address this challenge by exploring various multi-label classification frameworks to handle implicit discourse relation recognition. We show that multi-label classification methods don't depress performance for single-label prediction. Additionally, we give comprehensive analysis of results and data. Our work contributes to advancing the understanding and application of discourse relations and provide a foundation for the future study.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

2 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • TGEA: An Error-Annotated Dataset and Benchmark Tasks for TextGeneration from Pretrained Language Models cites Facilitating Contrastive Learning of Discourse Relational Senses by Exploiting the Hierarchy of Sense Relations
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers2

  1. TGEA: An Error-Annotated Dataset and Benchmark Tasks for TextGeneration from Pretrained Language ModelsJie He, Bo Peng, Yi Liao, Qun Liu et al.ACL 2021
  2. Discursive Circuits: How Do Language Models Understand Discourse Relations?Yisong Miao, Min-Yen KanEMNLP 2025

Builds on7

  1. Document-Level Relation Extraction with Adaptive Focal Loss and Knowledge DistillationQingyu Tan, Ruidan He, Lidong Bing, Hwee Tou NgACL Findings 2022 · 136 citations
  2. Order-Free Learning Alleviating Exposure Bias in Multi-Label ClassificationChe-Ping Tsai, Hung-yi LeeAAAI 2020 · 36 citations
  3. QADiscourse - Discourse Relations as QA Pairs: Representation, Crowdsourcing and BaselinesValentina Pyatkin, Ayal Klein, Reut Tsarfaty, Ido DaganEMNLP 2020 · 33 citations
  4. An Effective Deployment of Contrastive Learning in Multi-label Text ClassificationNankai Lin, Guanqiu Qin, Gang Wang, Dong Zhou et al.ACL Findings 2023 · 32 citations
  5. Facilitating Contrastive Learning of Discourse Relational Senses by Exploiting the Hierarchy of Sense RelationsWanqiu Long, Bonnie WebberEMNLP 2022 · 15 citations

Related papers

  1. A Label Dependence-Aware Sequence Generation Model for Multi-Level Implicit Discourse Relation RecognitionChangxing Wu, Liuwen Cao, Yubin Ge, Yang Liu et al.AAAI 2022 · 38 citations
  2. TransS-Driven Joint Learning Architecture for Implicit Discourse Relation RecognitionRuifang He, Jian Wang, Fengyu Guo, Yugui HanACL 2020 · 30 citations
  3. Weakly-Supervised Modeling of Contextualized Event Embedding for Discourse RelationsI-Ta Lee, Maria Leonor Pacheco, Dan GoldwasserEMNLP Findings 2020 · 15 citations
  4. Implicit Sense-labeled Connective Recognition as Text GenerationYui Oka, Tsutomu HiraoEMNLP Findings 2023 · 1 citation
  5. Discourse Sense Flows: Modelling the Rhetorical Style of Documents across Various DomainsRené Knaebel, Manfred StedeEMNLP Findings 2023
Dusk over the sea between two cliffs drawn in fine vertical lines