AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Discourse-Aware Graph Networks for Textual Logical Reasoning

Yinya Huang, Lemao Liu, Kun Xu, Meng Fang, Liang Lin, Xiaodan Liang

TPAMI 2023 · Graph learning › Knowledge and temporal graphs · approach: Logical query answering and rule reasoning

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
initialize nodes from contextual EDU embeddings instead of random embeddings (ablation)DAGNs · ReClor Testaccuracy (%): 56.40 -> 61.00Improved
add homogeneous variable edges within context and candidate nodes (ablation)DAGNs · ReClor Testaccuracy (%): 61.00 -> 59.30Hurt
use discourse-based edge linking instead of fully-connected linking (ablation)DAGNs · ReClor Testaccuracy (%): 56.10 -> 61.00Improved
use discourse-based edge linking instead of random linking (ablation)DAGNs · ReClor Testaccuracy (%): 55.90 -> 61.00Improved
distinguish explicit and implicit connective edge types instead of a single type (ablation)DAGNs · ReClor Testaccuracy (%): 57.70 -> 61.00Improved
use EDU nodes instead of clause nodes (ablation)DAGNs · ReClor Testaccuracy (%): 56.60 -> 61.00Improved
use EDU nodes instead of sentence nodes (ablation)DAGNs · ReClor Testaccuracy (%): 57.30 -> 61.00Improved
add logic edge reasoning (ablation)DAGNs · ReClor Testaccuracy (%): 59.80 -> 61.00Improved
add global graph representation (ablation)DAGNs · ReClor Testaccuracy (%): 60.10 -> 61.00Improved
add binary node types (ablation)DAGNs without edge reasoning and global representation · ReClor Testaccuracy (%): 58.70 -> 59.50Improved
add graph reasoning with hierarchical fusion (ablation)DAGNs · ReClor Testaccuracy (%): 52.00 -> 61.00Improved
add DAGNs logic graphs to RoBERTa-LargeRoBERTa-Large-MC · ReClor Testaccuracy (%): 55.60 -> 61.00Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy