Papers by Xuemeng Song

2 papers
Multi-source Semantic Graph-based Multimodal Sarcasm Explanation Generation (2023.acl-long)

Copied to clipboard

Challenge: Existing studies can only identify sarcastic post but could not give concrete explanation for why it is sarkastic.
Approach: They propose a multimodal sarcasm explanation scheme that generates a sentence for a social post to explain why it contains sarkasis.
Outcome: The proposed model outperforms existing methods on a public dataset.
MERIt: Meta-Path Guided Contrastive Learning for Logical Reasoning (2022.findings-acl)

Copied to clipboard

Challenge: Existing methods to infer logical relations with annotated training data suffer from over-fitting and poor generalization problems due to the dataset sparsity.
Approach: They propose a MEta-path guided contrastive learning method for logical ReasonIng of text that performs self-supervised pre-training on abundant unlabeled text data.
Outcome: The proposed method outperforms the baselines on two logical reasoning benchmarks with significant improvements.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations