Sep 7, 2024 · Moreover, we propose a novel constrained multi-layer CL approach to properly impose a constraint that the contrastive loss of higher layers ...
scholar.google.com › citations
Discourse relation recognition (DRR) aims to identify the existence of logical relations between two adjacent text spans in a discourse.
Apr 23, 2024 · Constrained Multi-Layer Contrastive Learning for Implicit Discourse Relationship Recognition. April 2024. Authors: Yiheng Wu at aian.online.
Sep 26, 2024 · Previous approaches to the task of implicit discourse relation recognition (IDRR) generally view it as a classification task.
Constrained Multi-Layer Contrastive Learning for Implicit Discourse Relationship Recognition ... Previous approaches to the task of implicit discourse relation ...
May 20, 2024 · Multi-level implicit discourse relation recognition (MIDRR) is a challenging task to recognize the hierarchical discourse relations between the ...
May 11, 2020 · In this paper, we propose a hierarchical multi-task neural network with a conditional random field layer (HierMTN-CRF) for multi-level IDRR.
This work proposes a novel GlObal and Local Hierarchy-aware Contrastive Framework (GOLF), to model two kinds of hierarchies with the aid of multi-task ...
Oct 21, 2024 · Recognizing implicit discourse relations between texts is challenging due to the absence of explicit connectives.
Missing: Layer | Show results with:Layer
In this paper, we propose NCPrompt, an NSP-based prompt learning and Contrastive learning method for IDRR.
Missing: Constrained Multi- Layer