mlsanityData to 7 Oct 2026

Revisiting Shallow Discourse Parsing in the PDTB-3: Handling Intra-sentential Implicits

arXiv 2204.00350 ↗First posted 1 Apr 2022cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

In the PDTB-3, several thousand implicit discourse relations were newly annotated textitwithin individual sentences, adding to the over 15,000 implicit relations annotated textitacross adjacent sentences in the PDTB-2. Given that the position of the arguments to these textitintra-sentential implicits is no longer as well-defined as with textitinter-sentential implicits, a discourse parser must identify both their location and their sense. That is the focus of the current work. The paper provides a comprehensive analysis of our results, showcasing model performance under different scenarios, pointing out limitations and noting future directions.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 10 of its 43 references that are in the map. First posted on arXiv 1 Apr 2022.

Builds on

10 of 43 references.

References · 10

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2018A Discourse-Aware Attention Model for Abstractive Summarization of Long Documentscited by 477
  5. 2018AllenNLP: A Deep Semantic Natural Language Processing Platformcited by 347
  6. 2018Deep Enhanced Representation for Implicit Discourse Relation Recognitioncited by 21
  7. 2018Improving Implicit Discourse Relation Classification by Modeling Inter-dependencies of Discourse Units in a Paragraphcited by 17
  8. 2016Recognizing Implicit Discourse Relations via Repeated Reading: Neural Networks with Multi-Level Attentioncited by 16
  9. 2020Extending Implicit Discourse Relation Recognition to the PDTB-3cited by 10
  10. 2019Zero-shot transfer for implicit discourse relation classificationcited by 5

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 1.

4 papers.